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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39810
    Prev
    Next
    INDEX
    Explanations

    conflict, communication, demonstrations

    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
    ized
    -0.58
    ه
    -0.49
    e
    -0.46
    st
    -0.42
    ised
    -0.40
    ize
    -0.40
    ization
    -0.40
     privatization
    -0.39
    ה
    -0.38
    ist
    -0.38
    POSITIVE LOGITS
    adaptiveStyles
    0.90
    uxxxx
    0.88
    PreferredItem
    0.85
     незавершена
    0.83
    InputBorder
    0.82
    CloseOperation
    0.81
     &___
    0.81
     Мексичка
    0.80
     كومونز
    0.78
     AssemblyCulture
    0.78
    Activations Density 0.044%

    No Known Activations