© 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. 5-CLT-HP
    7. 4703
    Prev
    Next
    INDEX
    Explanations

    Intelligence

    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
    neté
    -0.45
    تفصیلات
    -0.43
    bbler
    -0.43
    DataRow
    -0.43
     freezed
    -0.42
     חיצוניים
    -0.41
    Démographie
    -0.41
    Solución
    -0.41
    ্ষ
    -0.40
    FileDescriptor
    -0.39
    POSITIVE LOGITS
     ویکی‌پدیا
    0.68
    +#+#
    0.66
    hoven
    0.65
     виправивши
    0.60
    TabIndex
    0.60
    TintMode
    0.58
    AndEndTag
    0.57
    parsedMessage
    0.57
     Cmd
    0.56
     setColor
    0.56
    Activations Density 0.000%

    No Known Activations