© 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. 91922
    Prev
    Next
    INDEX
    Explanations

    p

    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
    OwnProperty
    -0.47
     externes
    -0.46
    hynch
    -0.44
    ihnachts
    -0.43
    baidu
    -0.43
     manhã
    -0.41
     poveznice
    -0.41
     esportivo
    -0.41
    Shortest
    -0.41
     "
    -0.41
    POSITIVE LOGITS
     faſt
    0.75
     Efq
    0.74
     Eſ
    0.73
    ArgsConstructor
    0.72
    AndroidJUnit
    0.70
    HasAnnotation
    0.70
     myſelf
    0.68
     ſi
    0.67
     itſelf
    0.67
    niosek
    0.67
    Activations Density 0.263%

    No Known Activations