© 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. 1-CLT-HP
    7. 728
    Prev
    Next
    INDEX
    Explanations

    Measurement units

    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
    NameInMap
    -0.85
    DockStyle
    -0.82
     resourceCulture
    -0.79
    دانشنامهٔ
    -0.78
     للاسماء
    -0.77
    IndentedString
    -0.77
     contextLoads
    -0.74
    __":
    -0.73
     Bourgoin
    -0.73
    invokeLater
    -0.73
    POSITIVE LOGITS
     (
    0.52
    M
    0.50
    mo
    0.49
    en
    0.48
    He
    0.47
    wide
    0.47
    ly
    0.47
    H
    0.47
    E
    0.47
    마
    0.47
    Activations Density 0.002%

    No Known Activations