© 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. 1-CLT-HP
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    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
    NUMX
    -0.73
     IBOutlet
    -0.70
    MemoryWarning
    -0.69
    setupUi
    -0.68
    Portail
    -0.67
     NSCoder
    -0.65
     CURIAM
    -0.65
    calaureate
    -0.64
    DockStyle
    -0.63
    InputBorder
    -0.61
    POSITIVE LOGITS
    bill
    0.49
    …
    0.47
     Phil
    0.47
     kon
    0.46
     Peter
    0.43
     bill
    0.43
     mountains
    0.43
     suite
    0.43
     defence
    0.42
    lag
    0.41
    Activations Density 0.088%

    No Known Activations