© 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. 1-CLT-HP
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    Su

    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
     Su
    -0.74
    lland
    -0.59
    aties
    -0.48
    EVAL
    -0.46
     ويكيپيديا
    -0.46
    xito
    -0.45
    arez
    -0.45
    ysuckle
    -0.44
    itaji
    -0.44
     su
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.84
    WithIOException
    0.73
    LookAnd
    0.71
    出版年
    0.71
    BeginContext
    0.67
     nakalista
    0.64
    InvalidProtocol
    0.64
    الحياه
    0.62
    RegistryLite
    0.61
    qtype
    0.60
    Activations Density 0.043%

    No Known Activations