© 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. 5-CLT-HP
    7. 92458
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     OFDb
    -0.76
    featureID
    -0.73
    SourceChecksum
    -0.72
     للمعارف
    -0.67
     voire
    -0.58
     SEDS
    -0.57
     onCreateView
    -0.55
     оригіналу
    -0.54
    ValueStyle
    -0.54
     فريبيس
    -0.53
    POSITIVE LOGITS
     Efq
    0.75
     neceff
    0.68
    WritableDatabase
    0.60
     perfons
    0.58
     poffe
    0.58
     myſelf
    0.57
     Majefty
    0.57
     poffible
    0.57
     Ruman
    0.56
     juſt
    0.55
    Activations Density 0.009%

    No Known Activations