© 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. 4333
    Prev
    Next
    INDEX
    Explanations

    standard English

    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
     catég
    -0.69
    esgue
    -0.68
    PreExecute
    -0.63
     nakalista
    -0.61
    Kjelder
    -0.61
    ArrowToggle
    -0.60
    CppCodeGen
    -0.59
    Diweddarwch
    -0.59
    tôi
    -0.57
    ifrance
    -0.57
    POSITIVE LOGITS
     kro
    0.53
     toch
    0.52
     travelers
    0.49
    DataAnnotations
    0.47
     numberOfRows
    0.46
     mok
    0.46
     everybody
    0.45
    pi
    0.44
    +"'
    0.44
    eak
    0.44
    Activations Density 0.012%

    No Known Activations