© 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. 1-CLT-HP
    7. 10208
    Prev
    Next
    INDEX
    Explanations

    Catholic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colch
    -0.42
     ordf
    -0.42
     समीक्षाओं
    -0.39
    inkov
    -0.38
    тей
    -0.38
    の一
    -0.37
     axis
    -0.37
    group
    -0.37
     aleg
    -0.37
     което
    -0.37
    POSITIVE LOGITS
    RectangleBorder
    0.83
    abetta
    0.69
    MLLoader
    0.69
     myſelf
    0.68
     thiệu
    0.64
     ModelRenderer
    0.64
     Chwiliwch
    0.63
    Predecesor
    0.62
    ſelf
    0.62
    asanjo
    0.62
    Activations Density 0.129%

    No Known Activations