© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    legal/formal language

    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
    atis
    -2.86
    Satis
    -0.77
     Satis
    -0.71
    satis
    -0.69
    atissimo
    -0.63
     satisfa
    -0.60
    atisme
    -0.59
    batis
    -0.59
     satisfying
    -0.56
     satisf
    -0.56
    POSITIVE LOGITS
     nakalista
    0.93
    parsedMessage
    0.87
     Chwiliwch
    0.81
     GoogleFonts
    0.77
    MergeFrom
    0.73
     Normdatei
    0.72
    adaptiveStyles
    0.72
    rrggbb
    0.71
     getItemId
    0.71
     itſelf
    0.71
    Activations Density 0.027%

    No Known Activations