© 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. 9460
    Prev
    Next
    INDEX
    Explanations

    ci

    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
    s
    -0.42
    ся
    -0.38
    jangan
    -0.37
    Ț
    -0.37
    ïdes
    -0.37
    чиков
    -0.36
    ěj
    -0.36
    oose
    -0.36
    LocalizedString
    -0.36
    FTFY
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.79
    ArgsConstructor
    0.78
    styleable
    0.77
     समीक्षक
    0.77
     ivelany
    0.75
     ویکی‌آمباردا
    0.75
    MLLoader
    0.75
     NSCoder
    0.70
    UnknownFieldSet
    0.70
     Мексичка
    0.70
    Activations Density 0.069%

    No Known Activations