© 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. 43976
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    mybatisplus
    -0.66
    itinéraire
    -0.57
    بوابة
    -0.54
    Expedia
    -0.54
     geprek
    -0.52
    WireFormatLite
    -0.51
     scolaires
    -0.50
    Chains
    -0.48
     esternos
    -0.48
     faibles
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.66
    findpost
    0.64
     crossorigin
    0.61
     moll
    0.59
    FileInput
    0.57
    SourceChecksum
    0.55
    subsection
    0.54
     spieg
    0.54
    windowFixed
    0.54
    bew
    0.54
    Activations Density 0.220%

    No Known Activations