© 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. 96120
    Prev
    Next
    INDEX
    Explanations

    labels and naming

    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
     considérons
    -0.58
     initComponents
    -0.54
     ucapnya
    -0.50
    inheritDoc
    -0.49
    ../../
    -0.48
    atrième
    -0.47
    EDEFAULT
    -0.46
     Cok
    -0.45
    ttino
    -0.45
     onPostExecute
    -0.44
    POSITIVE LOGITS
     diagrams
    0.81
    GEBURTSDATUM
    0.81
     diagram
    0.64
     Diagrams
    0.64
     Мексичка
    0.62
    Spoljašnje
    0.56
    Tembelea
    0.56
     Diagram
    0.56
    titleMargin
    0.55
    diagram
    0.54
    Activations Density 0.000%

    No Known Activations