© 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. 20-CLT-HP
    7. 72121
    Prev
    Next
    INDEX
    Explanations

    Foreign language words

    np_max-act-logits · 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
    ConstraintMaker
    -0.75
     незавершена
    -0.73
     كومونز
    -0.71
     ModelExpression
    -0.69
     ویکی‌پدیا
    -0.66
    Parcelize
    -0.65
    titleMargin
    -0.65
    ArgumentParser
    -0.64
    matchCondition
    -0.63
    +#+
    -0.63
    POSITIVE LOGITS
    strix
    0.50
     tài
    0.45
     SAX
    0.43
     domani
    0.41
    Creation
    0.41
    백
    0.41
     separat
    0.40
     Caz
    0.40
     méta
    0.40
    ことで
    0.39
    Activations Density 0.002%

    No Known Activations