© 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. 20-CLT-HP
    7. 72438
    Prev
    Next
    INDEX
    Explanations

    code/data context

    np_max-act-logits · 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
     Fourth
    -0.77
     Four
    -0.75
    FOUR
    -0.74
     FOUR
    -0.73
     keempat
    -0.70
    ④
    -0.69
     FOURTH
    -0.67
     Fournier
    -0.67
    Fourth
    -0.66
     quartet
    -0.63
    POSITIVE LOGITS
    styleType
    0.67
     penta
    0.64
    ScopeManager
    0.61
    errHandler
    0.61
    penta
    0.59
    fifths
    0.54
     Fifth
    0.52
    Fifth
    0.51
    bootstrapcdn
    0.50
     Diego
    0.50
    Activations Density 0.046%

    No Known Activations