© 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. 4-CLT-HP
    7. 3328
    Prev
    Next
    INDEX
    Explanations

    People and their roles

    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
     kasarigan
    -0.52
     invokingState
    -0.50
     للمعارف
    -0.49
    ny
    -0.46
    temporary
    -0.44
     eml
    -0.43
    DockStyle
    -0.43
     temporary
    -0.42
     ucc
    -0.41
     Fi
    -0.40
    POSITIVE LOGITS
    цездатний
    1.00
    ArgsConstructor
    0.77
    Personensuche
    0.70
     Roskov
    0.69
    mybatisplus
    0.69
     LoggerFactory
    0.66
    NUMX
    0.65
    HasAnnotation
    0.65
    ModelBuilder
    0.63
     fathoms
    0.62
    Activations Density 0.001%

    No Known Activations