© 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. 1-CLT-HP
    7. 9723
    Prev
    Next
    INDEX
    Explanations

    author

    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
     author
    -1.20
    author
    -0.99
     Author
    -0.96
    Author
    -0.89
     authors
    -0.83
     AUTHOR
    -0.76
     Authors
    -0.66
    authors
    -0.65
    AUTHOR
    -0.61
    Authors
    -0.61
    POSITIVE LOGITS
    ing
    0.92
    ises
    0.59
    Hentet
    0.59
    AMIENTO
    0.57
    ised
    0.55
    ING
    0.55
    ie
    0.54
    GeneratedCode
    0.53
    tamiento
    0.53
    ed
    0.52
    Activations Density 0.036%

    No Known Activations