© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74799
    Prev
    Next
    INDEX
    Explanations

    To be

    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
     keep
    -0.62
     keeps
    -0.62
     Keeps
    -0.61
     Fixing
    -0.59
    Fixing
    -0.57
    keeps
    -0.56
    continues
    -0.56
     مرئيه
    -0.55
     remain
    -0.55
     Keep
    -0.54
    POSITIVE LOGITS
     ویکی‌پدیا
    0.52
    RefNanny
    0.52
     maintained
    0.50
    لينكات
    0.49
    ConstraintMaker
    0.47
     left
    0.47
     not
    0.47
    avigation
    0.46
    RRect
    0.46
    not
    0.46
    Activations Density 0.001%

    No Known Activations