© 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. 9277
    Prev
    Next
    INDEX
    Explanations

    historic/historical

    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
    expandindo
    -0.79
    windowFixed
    -0.67
    }/${
    -0.53
    Datuak
    -0.53
     nahilalakip
    -0.50
    oredCriteria
    -0.50
    smithy
    -0.48
     traditional
    -0.46
    tanleria
    -0.45
     traditionelle
    -0.45
    POSITIVE LOGITS
     doubtnut
    0.65
     CreateTagHelper
    0.57
    ClientSize
    0.56
     Benfica
    0.56
    upuncture
    0.56
     LEYENDO
    0.56
    meneu
    0.55
     ibiza
    0.54
    Apothe
    0.54
     apothe
    0.54
    Activations Density 0.007%

    No Known Activations