© 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. 95112
    Prev
    Next
    INDEX
    Explanations

    only

    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
    enumi
    -0.68
     الحره
    -0.66
     ffilmiau
    -0.61
     Daarom
    -0.49
     useParams
    -0.49
    HasForeignKey
    -0.48
    ContentAsync
    -0.48
    IVEREF
    -0.48
     EconPapers
    -0.47
     Drapeau
    -0.47
    POSITIVE LOGITS
     in
    0.87
     with
    0.77
     for
    0.77
     because
    0.76
     from
    0.63
     between
    0.56
     on
    0.53
    usermodel
    0.53
    ‍♀
    0.53
     while
    0.52
    Activations Density 0.002%

    No Known Activations