© 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. 45771
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     فريبيس
    -0.91
    Lähteet
    -0.74
    MigrationBuilder
    -0.70
    .*")]
    -0.66
     rhestr
    -0.60
    AdapterFactory
    -0.60
    CloseOperation
    -0.58
    ंदीखरीदारी
    -0.57
    ArgsConstructor
    -0.57
    RunWith
    -0.57
    POSITIVE LOGITS
     oreilles
    0.56
     magát
    0.53
    帖最后由
    0.52
     Besøkt
    0.49
     jambes
    0.49
     doigts
    0.49
     saveurs
    0.48
    новништво
    0.47
     entendimiento
    0.46
     comprendere
    0.46
    Activations Density 0.005%

    No Known Activations