© 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. 45766
    Prev
    Next
    INDEX
    Explanations

    just

    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
     estimés
    -0.52
     and
    -0.47
     épouse
    -0.46
     kosong
    -0.46
     tersebut
    -0.45
     propOrder
    -0.44
     époux
    -0.44
    μερα
    -0.44
    sifs
    -0.43
     bättre
    -0.43
    POSITIVE LOGITS
     naming
    0.82
     listing
    0.77
     mentioning
    0.76
     acting
    0.72
     drawing
    0.72
     offering
    0.71
     claiming
    0.70
     specifying
    0.70
     asking
    0.69
     للمعارف
    0.69
    Activations Density 0.425%

    No Known Activations