© 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. 95079
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
    PropertyChanging
    -0.52
     purpoſe
    -0.47
     bawat
    -0.47
     raiſ
    -0.47
     pamamagitan
    -0.47
     uſ
    -0.44
     ſaid
    -0.44
     pienso
    -0.44
     poffe
    -0.44
     ſal
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.93
    Rüyada
    0.78
     AssemblyTitle
    0.77
     يتيمه
    0.76
    getDescriptor
    0.73
    matchCondition
    0.70
    vician
    0.68
    <?
    0.67
    bkz
    0.67
    addCriterion
    0.65
    Activations Density 0.003%

    No Known Activations