© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42427
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code

    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
     of
    -0.55
     Pineda
    -0.49
    er
    -0.48
    WhereInput
    -0.48
    ing
    -0.48
    AutoScaleMode
    -0.47
    ogon
    -0.47
      (
    -0.46
    asan
    -0.46
    наче
    -0.46
    POSITIVE LOGITS
     برانيه
    0.69
     unknownFields
    0.58
    UIControlState
    0.55
    runApp
    0.53
     betweenstory
    0.53
    DoubleQuotes
    0.53
     ویکی‌پدیا
    0.52
     vPvB
    0.52
    SceneManagement
    0.50
     SqlCommand
    0.49
    Activations Density 0.055%

    No Known Activations