© 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. 0-CLT-HP
    4. 94984
    Prev
    Next
    INDEX
    Explanations

    colin

    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
    INARY
    -2.33
    colin
    -1.76
    inary
    -0.83
     surla
    -0.82
     OFDb
    -0.73
     Colin
    -0.71
    IsMutable
    -0.70
    DoubleQuotes
    -0.68
     متعلقه
    -0.66
     BoxDecoration
    -0.62
    POSITIVE LOGITS
     تضيفلها
    0.55
     समीक्षाओं
    0.54
    RatingBar
    0.53
    weza
    0.51
     pageContext
    0.48
    ExecuteReader
    0.48
     ménages
    0.47
    HideFlags
    0.47
    umentación
    0.46
    blos
    0.45
    Activations Density 0.145%

    No Known Activations