© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    Medicine, history, and disease

    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
     fumée
    -0.74
     démocr
    -0.65
     noires
    -0.61
     financières
    -0.60
     ferons
    -0.59
     descendre
    -0.58
     défaite
    -0.57
     roulant
    -0.57
     confiance
    -0.56
     nettoy
    -0.56
    POSITIVE LOGITS
    ⓧ
    0.59
    Tembelea
    0.54
    ContentAsync
    0.53
    MigrationBuilder
    0.52
    Gambas
    0.50
     Cardona
    0.49
     Beaufort
    0.46
    okhttp
    0.46
    ]}>
    0.46
    ]")]
    0.45
    Activations Density 0.152%

    No Known Activations