© 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. 4-CLT-HP
    7. 4481
    Prev
    Next
    INDEX
    Explanations

    the

    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
     فريبيس
    -0.66
     Daß
    -0.64
    خة
    -0.62
     thoſe
    -0.61
     kaarangay
    -0.61
    contentLoaded
    -0.61
     mijne
    -0.61
    expandindo
    -0.61
     Houſe
    -0.60
     incontra
    -0.59
    POSITIVE LOGITS
     propOrder
    0.66
     rapid
    0.57
     Empieza
    0.54
     increasing
    0.53
     fast
    0.52
     surla
    0.51
    Eloquent
    0.50
     increased
    0.50
    ēj
    0.49
     rapidly
    0.48
    Activations Density 0.014%

    No Known Activations