© 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. 5-CLT-HP
    7. 3325
    Prev
    Next
    INDEX
    Explanations

    per

    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
     '\\;'
    -0.73
    loroethene
    -0.50
     الحره
    -0.49
    invokeLater
    -0.48
    ArgsConstructor
    -0.47
     StatefulWidget
    -0.46
     ***!
    -0.46
    ogeneity
    -0.46
    urtstag
    -0.45
    rhosis
    -0.45
    POSITIVE LOGITS
     season
    0.60
     незавершена
    0.57
     semester
    0.57
    extAlignment
    0.57
    empêcher
    0.54
     transférez
    0.53
     week
    0.53
     seizoen
    0.52
    ergies
    0.52
    ✨:
    0.51
    Activations Density 0.001%

    No Known Activations