© 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. 97687
    Prev
    Next
    INDEX
    Explanations

    Donovan

    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
     alike
    -0.88
     bud
    -0.56
     Donovan
    -0.47
     Sal
    -0.46
    ftan
    -0.44
    ranton
    -0.41
     lib
    -0.40
     sal
    -0.40
    Donovan
    -0.39
    ющий
    -0.39
    POSITIVE LOGITS
     myſelf
    0.81
    ualaikum
    0.75
    )];
    0.75
    auteuil
    0.75
     itſelf
    0.74
    enumii
    0.71
     ويكيميديا
    0.69
    躇
    0.68
    ilities
    0.67
    invokeLater
    0.66
    Activations Density 0.111%

    No Known Activations