© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93801
    Prev
    Next
    INDEX
    Explanations

    Marys

    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
    HtmlAttribute
    -0.66
    جغرافيا
    -0.65
    sizeCache
    -0.60
    inSlope
    -0.59
     Lordships
    -0.56
     mohair
    -0.56
    canna
    -0.56
     Lagrangian
    -0.54
    pexpr
    -0.54
     Turing
    -0.53
    POSITIVE LOGITS
    migrationBuilder
    0.70
    Capsule
    0.48
     زم
    0.47
    styleUrls
    0.47
    LikeLike
    0.47
    Krak
    0.46
     sute
    0.46
    Hentet
    0.46
    Archive
    0.45
    tinya
    0.45
    Activations Density 0.001%

    No Known Activations