© 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. 1-CLT-HP
    7. 273
    Prev
    Next
    INDEX
    Explanations

    it

    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
     his
    -0.94
    彼の
    -0.76
     him
    -0.75
     himself
    -0.75
    '
    -0.71
    但他
    -0.71
    ’
    -0.71
    his
    -0.71
    His
    -0.69
     seinem
    -0.69
    POSITIVE LOGITS
    Jeografia
    0.86
    PreferredItem
    0.79
    Viited
    0.79
     Roskov
    0.71
     Catawiki
    0.71
     الرياضيه
    0.70
    Abit
    0.70
    GEBURTS
    0.68
    ]<<"
    0.67
     незавершена
    0.66
    Activations Density 0.011%

    No Known Activations