© 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. 22-RES-MATRYOSHKA-DC
    7. 2680
    Prev
    Next
    INDEX
    Explanations

    code comments in C files

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^^
    -0.54
    Toponymie
    -0.51
    <strong>
    -0.50
    HttpException
    -0.48
    ^
    -0.47
     geprek
    -0.46
    bech
    -0.45
     carreaux
    -0.45
     saurait
    -0.44
    \$
    -0.44
    POSITIVE LOGITS
    /*
    1.86
     /*
    1.52
    <i>
    1.18
    /*"
    1.17
    <em>
    1.17
    /*",
    1.13
    +/*
    1.03
    (/*
    1.03
    /*
    0.99
    }/*
    0.99
    Activations Density 0.021%

    No Known Activations