© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    sports

    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
     internacionales
    -0.58
    international
    -0.57
     international
    -0.56
    International
    -0.52
     International
    -0.50
    <bos>
    -0.50
    :✨
    -0.48
     internacionais
    -0.46
     międzynarod
    -0.46
    thousand
    -0.46
    POSITIVE LOGITS
    homonymie
    0.78
     disambiguazione
    0.77
    Rhestr
    0.68
     مشين
    0.63
     CURIAM
    0.59
     للاسماء
    0.59
     Messe
    0.59
    bolista
    0.58
    商品説明
    0.57
     برانيه
    0.57
    Activations Density 0.006%

    No Known Activations