© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96027
    Prev
    Next
    INDEX
    Explanations

    appar

    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
     verschieden
    -0.65
    titleMargin
    -0.63
    RegressionTest
    -0.63
     forskjellige
    -0.63
    depending
    -0.60
    addCriterion
    -0.60
    diferentes
    -0.60
     verschied
    -0.60
     różne
    -0.59
     depending
    -0.59
    POSITIVE LOGITS
    ngdoc
    0.75
    via
    0.52
    per
    0.49
    .
    0.49
     Subsequent
    0.48
    defn
    0.47
     استنادى
    0.47
     serve
    0.46
    their
    0.46
    DataAnnotations
    0.46
    Activations Density 0.029%

    No Known Activations