© 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. 4-CLT-HP
    7. 4599
    Prev
    Next
    INDEX
    Explanations

    Internet/code excerpts

    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
    出版年
    -1.02
    WebElementEntity
    -0.90
    TintMode
    -0.85
    makeConstraints
    -0.77
    IntoConstraints
    -0.77
     EconPapers
    -0.74
    ProgressHUD
    -0.73
     ویکی‌پدیای
    -0.72
    NameInMap
    -0.72
     imageNamed
    -0.72
    POSITIVE LOGITS
     a
    0.73
    <bos>
    0.65
    XmlAccessType
    0.52
     that
    0.48
     covering
    0.48
     treating
    0.47
     an
    0.46
    a
    0.46
     celebrating
    0.45
     The
    0.45
    Activations Density 0.002%

    No Known Activations