© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    integral

    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
    .
    -0.52
     seguida
    -0.50
     supprim
    -0.46
    R
    -0.43
    a
    -0.42
     considerado
    -0.42
    (
    -0.39
    r
    -0.39
     délais
    -0.38
     endast
    -0.37
    POSITIVE LOGITS
     myſelf
    1.00
     Theſe
    0.96
     Efq
    0.92
     cauſe
    0.91
     Diſ
    0.91
     purpoſe
    0.91
     ſeveral
    0.90
     ―――――
    0.89
     whoſe
    0.88
    ſelves
    0.87
    Activations Density 0.018%

    No Known Activations