One of the challenges of modern cosmology is to discriminate among the many models of inflation which are able to predict a scale invariant spetrum as observed in the Cosmic Microwave Backround. One of the features which could help in this effort is non-Gaussianity, namely if the random seeds of the initial perturbations are to be described with higher than 2-point statistics. Non-Gaussianity in its simplest form is generally parametrized by a non-linearity parameter, fNL.

With the advent of large scale galaxy surveys, constraints on primordial non-Gaussianity are expected to reach order O(fNL) ~1. In order to fully exploit the potential of these future surveys, a deep theoretical understanding of the signatures imprinted by primordial non-Gaussianity on the large scale structure of the Universe is necessary. In this talk we will introduce the peak approach to halo clustering, which provides a framework to predict such signatures. We will show in detail how this prediction is calculated and compare it to other methods (such as the peak-background split ansatz).