© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 2386
    Prev
    Next
    INDEX
    Explanations

    the word "introduction" that begins a section of an article

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hebron
    -0.65
    NOTIFY
    -0.65
     spira
    -0.64
     Entries
    -0.63
     Inscrivez
    -0.63
    spira
    -0.62
    Архівовано
    -0.61
    WebElementEntity
    -0.61
     Suivez
    -0.61
     Schall
    -0.60
    POSITIVE LOGITS
    Introduction
    3.00
     Introduction
    2.80
     INTRODUCTION
    2.53
    INTRODUCTION
    2.48
     introduction
    2.44
    introduction
    2.31
    Introducción
    2.06
     introductions
    1.95
     Introducción
    1.92
    Introdução
    1.87
    Activations Density 0.009%

    No Known Activations