© 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. 5-CLT-HP
    7. 1968
    Prev
    Next
    INDEX
    Explanations

    surround

    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
     moindre
    -0.52
    ç
    -0.45
    Hand
    -0.45
    jl
    -0.44
    jd
    -0.44
    hamilan
    -0.44
    jà
    -0.44
    j
    -0.43
    cales
    -0.43
     Hand
    -0.42
    POSITIVE LOGITS
    sound
    0.88
     autorytatywna
    0.83
    Autoritní
    0.82
    出版年
    0.81
     sound
    0.78
     дописавши
    0.77
     Мексичка
    0.72
    ingly
    0.71
    transQ
    0.71
    UserScript
    0.71
    Activations Density 0.009%

    No Known Activations