© 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. 1969
    Prev
    Next
    INDEX
    Explanations

    way

    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
     Certainly
    -0.91
     certainly
    -0.82
    Certainly
    -0.81
     indeed
    -0.79
    certainly
    -0.77
     inderdaad
    -0.71
    確かに
    -0.71
     effectivement
    -0.69
    的确
    -0.68
     ciertamente
    -0.67
    POSITIVE LOGITS
     invece
    0.71
     autorytatywna
    0.63
    則是
    0.59
     either
    0.58
     instead
    0.57
    bootstrapcdn
    0.56
     مواليد
    0.55
     istället
    0.54
    :✨
    0.54
    OCCURRED
    0.53
    Activations Density 0.002%

    No Known Activations