© 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. 97626
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
     pain
    -0.97
     فريبيس
    -0.94
     للمعارف
    -0.94
     Chwiliwch
    -0.92
    pain
    -0.90
    Pain
    -0.88
     PAIN
    -0.86
     Pain
    -0.85
     ChromeDriver
    -0.83
    roughts
    -0.83
    POSITIVE LOGITS
    s
    1.26
    ing
    0.77
    es
    0.76
    ful
    0.71
    en
    0.70
    an
    0.70
    al
    0.68
    ous
    0.66
    y
    0.66
    ary
    0.63
    Activations Density 0.088%

    No Known Activations