© 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. 2029
    Prev
    Next
    INDEX
    Explanations

    to

    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
    queryInterface
    -0.68
    MeasureSpec
    -0.62
     AssemblyCulture
    -0.59
     ModelExpression
    -0.57
     مشين
    -0.55
     незавершена
    -0.55
     Paglinawan
    -0.55
    Referències
    -0.54
    LabelTagHelper
    -0.54
    ilarang
    -0.52
    POSITIVE LOGITS
     Asian
    0.59
     Caucasian
    0.52
    paravant
    0.52
     Haz
    0.51
     Jewell
    0.50
    OGND
    0.48
     Asia
    0.48
     human
    0.47
     us
    0.47
     Jewish
    0.47
    Activations Density 0.002%

    No Known Activations