© 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. 4-CLT-HP
    7. 1024
    Prev
    Next
    INDEX
    Explanations

    iz

    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
    terie
    -0.57
    migrationBuilder
    -0.54
    ITRE
    -0.54
    rítica
    -0.54
    Erreferentziak
    -0.53
    `{.
    -0.52
    /***/
    -0.52
    RuleContext
    -0.51
    maline
    -0.51
    OpenHelper
    -0.51
    POSITIVE LOGITS
    ye
    0.54
    supp
    0.52
    الإنجليزية
    0.52
    ya
    0.51
     Нам
    0.49
    Supp
    0.48
    Dış
    0.48
    Ẩ
    0.48
     silêncio
    0.48
     judicia
    0.47
    Activations Density 0.020%

    No Known Activations