© 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. 92026
    Prev
    Next
    INDEX
    Explanations

    Dakota

    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
    InSection
    -0.92
     Theſe
    -0.86
    GraphicsUnit
    -0.83
     iſt
    -0.82
     ſeveral
    -0.78
     Monfieur
    -0.78
    wiſe
    -0.77
     myſelf
    -0.76
     Conſ
    -0.74
    RectangleBorder
    -0.73
    POSITIVE LOGITS
    als
    0.63
    لوب
    0.49
    ,
    0.49
    l
    0.48
    sm
    0.47
    Help
    0.47
    H
    0.47
    R
    0.46
    S
    0.46
     help
    0.46
    Activations Density 0.175%

    No Known Activations