© 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. 91139
    Prev
    Next
    INDEX
    Explanations

    columnist

    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
    ls
    -0.53
    @
    -0.50
    the
    -0.48
     researchers
    -0.48
     educated
    -0.46
     of
    -0.45
    })
    -0.45
    ↵
    -0.44
    ://
    -0.43
    のように
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.79
     NSCoder
    0.74
     تضيفلها
    0.70
    Démographie
    0.69
     становника
    0.67
    Vidite
    0.67
     ویکی‌پدیای
    0.66
    fjspx
    0.66
     '\\;'
    0.65
     arşivlendi
    0.65
    Activations Density 1.810%

    No Known Activations