© 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. 0-CLT-HP
    7. 94248
    Prev
    Next
    INDEX
    Explanations

    of

    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
    tvguidetime
    -0.95
     كومونز
    -0.76
     CreateTagHelper
    -0.73
     ModelExpression
    -0.72
     defaultstate
    -0.71
     للمعارف
    -0.71
    URLException
    -0.68
     BoxFit
    -0.67
     صوتيه
    -0.67
    uxxxx
    -0.65
    POSITIVE LOGITS
    ьаж
    0.56
     financiación
    0.49
    🗳
    0.45
    Ariel
    0.45
     Mena
    0.44
    uatu
    0.44
     Qua
    0.43
    chua
    0.43
     Miele
    0.43
    ILON
    0.43
    Activations Density 0.087%

    No Known Activations