© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40032
    Prev
    Next
    INDEX
    Explanations

    government/official documents

    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
    s
    -0.57
    ing
    -0.56
    irs
    -0.52
    oirs
    -0.49
    ycle
    -0.45
    er
    -0.44
    a
    -0.43
     brick
    -0.43
     cable
    -0.43
    edly
    -0.42
    POSITIVE LOGITS
    InjectAttribute
    0.83
     kasarigan
    0.79
    JspWriter
    0.72
    expandindo
    0.70
     برانيه
    0.69
     للمعارف
    0.68
     تانيه
    0.68
    ⓧ
    0.68
     المعيارى
    0.67
     समीक्षाओं
    0.66
    Activations Density 0.166%

    No Known Activations