© 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. 0-CLT-HP
    7. 92061
    Prev
    Next
    INDEX
    Explanations

    Yay

    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
    ness
    -0.81
    s
    -0.72
    d
    -0.70
    ting
    -0.67
    alism
    -0.65
    uality
    -0.63
    ing
    -0.61
    sad
    -0.60
    sing
    -0.60
    ergies
    -0.60
    POSITIVE LOGITS
     كومونز
    0.66
    Autoritní
    0.65
     précédents
    0.54
     arbejds
    0.53
     onCancelled
    0.53
     neuesten
    0.51
    tymologie
    0.50
    NameInMap
    0.49
    FillColor
    0.49
    disposing
    0.48
    Activations Density 0.115%

    No Known Activations