© 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. 0-CLT-HP
    7. 41095
    Prev
    Next
    INDEX
    Explanations

    human

    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
     Efq
    -0.95
     auffi
    -0.73
     iſt
    -0.72
     myſelf
    -0.72
     AssemblyCulture
    -0.70
     незавершена
    -0.69
     Perſ
    -0.69
    .‏
    -0.69
    ſelf
    -0.68
     ་་
    -0.68
    POSITIVE LOGITS
    ity
    0.77
    age
    0.54
    ITY
    0.54
     nakalista
    0.47
    uality
    0.45
    ोग
    0.43
    êmio
    0.42
    Дереккөздер
    0.40
    IDO
    0.40
    AGE
    0.40
    Activations Density 1.750%

    No Known Activations