© 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. 1-CLT-HP
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    station

    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
    omitempty
    -0.62
    millimeters
    -0.55
    statistics
    -0.50
     mammary
    -0.50
     сожалению
    -0.50
    ITU
    -0.50
    jsoup
    -0.49
     statistics
    -0.49
    seigneur
    -0.48
    dike
    -0.48
    POSITIVE LOGITS
     lenker
    0.67
     للاسماء
    0.62
    Kapcsolódó
    0.55
    adaptiveStyles
    0.52
     defaultstate
    0.51
     Shelves
    0.51
     архивлан
    0.51
    ArrowToggle
    0.50
    lasma
    0.50
     BoxDecoration
    0.48
    Activations Density 0.007%

    No Known Activations