© 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. 38760
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
     ſche
    -0.98
    ViewFeatures
    -0.96
     myſelf
    -0.94
    ſelf
    -0.94
     iſt
    -0.93
     purpoſe
    -0.89
     Anſ
    -0.88
     ashamed
    -0.87
     nahilalakip
    -0.87
     greateſt
    -0.85
    POSITIVE LOGITS
     of
    0.78
     to
    0.78
    es
    0.62
    s
    0.56
    a
    0.54
    ه
    0.54
    nes
    0.53
    e
    0.52
     so
    0.51
     re
    0.50
    Activations Density 0.153%

    No Known Activations