© 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. 18-RES-MATRYOSHKA-DC
    7. 652
    Prev
    Next
    INDEX
    Explanations

    the word "this"

    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.18.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.18.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
    脚注の使い方
    -0.88
    httphttps
    -0.85
    WindowConstants
    -0.78
     SqlDbType
    -0.76
    Gön
    -0.75
     незавершена
    -0.74
    aarrggbb
    -0.74
    XmlAccessorType
    -0.72
    )");
    -0.70
    .[/
    -0.70
    POSITIVE LOGITS
     week
    0.53
    DBNull
    0.49
     guy
    0.46
     year
    0.46
     attre
    0.45
    week
    0.43
    constructor
    0.43
    //
    0.43
     x
    0.42
    vdash
    0.42
    Activations Density 0.464%

    No Known Activations