© 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. 20-CLT-HP
    7. 71977
    Prev
    Next
    INDEX
    Explanations

    Code, technical documents

    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
     للاسماء
    -0.97
    tagHelperRunner
    -0.90
    الإنجليزية
    -0.88
    providedIn
    -0.88
    ReusableCell
    -0.87
    ValueStyle
    -0.85
     Chwiliwch
    -0.82
     فريبيس
    -0.82
     ویکی‌پدی
    -0.82
    PreferredItem
    -0.80
    POSITIVE LOGITS
     once
    0.51
    res
    0.47
     res
    0.46
     global
    0.45
    le
    0.37
     mondiale
    0.37
     remor
    0.36
    وصف
    0.35
     đẩy
    0.35
     laci
    0.34
    Activations Density 0.000%

    No Known Activations