© 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
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6252
    Prev
    Next
    INDEX
    Explanations

    segments of structured markup code or comments within documents

    oai_token-act-pair · gpt-4.1-nano
    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
     Pact
    -0.50
    brainly
    -0.48
     الرح
    -0.47
     neighbors
    -0.47
     gâteau
    -0.46
     Eilish
    -0.46
     EEA
    -0.46
    nap
    -0.46
     demikian
    -0.45
     manteau
    -0.45
    POSITIVE LOGITS
    <!--
    3.84
     <!--
    2.67
    <!--
    2.09
    ><!--
    2.05
    "><!--
    1.77
    <!
    1.53
    {/*
    1.23
    <!--<
    1.13
    <!--[
    1.07
    脚注の使い方
    1.06
    Activations Density 0.007%

    No Known Activations