© 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. 91078
    Prev
    Next
    INDEX
    Explanations

    soaring

    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
     talk
    -0.94
    talk
    -0.90
     Talk
    -0.82
    Talk
    -0.80
    s
    -0.56
    ska
    -0.56
     TALK
    -0.56
     scholars
    -0.51
     analysts
    -0.50
    ی
    -0.50
    POSITIVE LOGITS
    +#+
    0.80
     myſelf
    0.77
     enfans
    0.73
     fidé
    0.72
    ंदीखरीदारी
    0.69
     élas
    0.67
     zelve
    0.67
     humain
    0.67
     ब्रेकडाउन
    0.65
    日閲覧
    0.65
    Activations Density 0.372%

    No Known Activations