© 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. 4-CLT-HP
    7. 3366
    Prev
    Next
    INDEX
    Explanations

    can

    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
    دانشنامهٔ
    -0.89
    windowFixed
    -0.81
    DockStyle
    -0.79
     ProtoMessage
    -0.71
    CloseOperation
    -0.70
    fjspx
    -0.63
     ویکی‌پدی
    -0.62
    oredCriteria
    -0.60
    ьаж
    -0.60
    astéroïdes
    -0.60
    POSITIVE LOGITS
     happen
    0.89
     Happen
    0.80
    all
    0.69
    happen
    0.68
     all
    0.68
    \{\\
    0.66
     happens
    0.61
     ALL
    0.59
     HAPP
    0.59
    All
    0.58
    Activations Density 0.006%

    No Known Activations