© 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. 38896
    Prev
    Next
    INDEX
    Explanations

    due

    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
     enfans
    -0.45
     batalha
    -0.44
     (
    -0.42
     avant
    -0.41
    /
    -0.41
    madı
    -0.41
     feltro
    -0.40
     carreras
    -0.39
     jäsen
    -0.38
     charla
    -0.38
    POSITIVE LOGITS
     Roskov
    0.99
     pinulongan
    0.99
     BoxDecoration
    0.95
    __':
    0.95
    parsedMessage
    0.91
     wireType
    0.90
    migrationBuilder
    0.88
    ResumeLayout
    0.87
     Мексичка
    0.86
     تضيفلها
    0.85
    Activations Density 0.027%

    No Known Activations