© 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. 5-CLT-HP
    7. 1158
    Prev
    Next
    INDEX
    Explanations

    rest

    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
     communiquez
    -0.66
    memberOf
    -0.48
    PointerException
    -0.46
    InBackground
    -0.45
     Sardin
    -0.45
    rawtypes
    -0.44
    Diwedd
    -0.44
     crossorigin
    -0.44
     answering
    -0.44
     geldig
    -0.43
    POSITIVE LOGITS
    phus
    0.63
    aged
    0.62
    aging
    0.61
     Betracht
    0.59
    fallen
    0.58
    orer
    0.56
     ligiloj
    0.56
    ungalow
    0.55
    atious
    0.55
    orations
    0.54
    Activations Density 0.003%

    No Known Activations