© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    spies

    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
    red
    -0.43
    lab
    -0.43
    pla
    -0.42
    belt
    -0.41
    mo
    -0.41
    board
    -0.41
    RED
    -0.40
    errHandler
    -0.40
    Lab
    -0.39
    M
    -0.39
    POSITIVE LOGITS
    DrawerToggle
    0.75
     myſelf
    0.73
     للمعارف
    0.72
     للاسماء
    0.71
    FTFY
    0.71
     itſelf
    0.70
     againſt
    0.69
    lgari
    0.68
    MigrationBuilder
    0.68
    ztály
    0.67
    Activations Density 0.006%

    No Known Activations