© 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. 4-CLT-HP
    7. 146
    Prev
    Next
    INDEX
    Explanations

    period

    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
    yntaxException
    -0.68
    RuleContext
    -0.67
    DialogContent
    -0.66
    apeno
    -0.64
    GroupLayout
    -0.62
    LayoutParams
    -0.61
    ISODE
    -0.60
    횟
    -0.59
     بتاريخ
    -0.59
    Geschiedenis
    -0.59
    POSITIVE LOGITS
    InSection
    0.54
    GOTREF
    0.53
    "]]
    0.52
    外部リンク
    0.44
     nor
    0.43
    springen
    0.43
    removeAll
    0.42
     سازی
    0.41
     TextAppearance
    0.40
    InputBorder
    0.39
    Activations Density 0.038%

    No Known Activations