© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16210
    Prev
    Next
    INDEX
    Explanations

    determined

    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
    Negative Logits
    determined
    -0.62
    SourceChecksum
    -0.56
     determined
    -0.55
     déterminé
    -0.53
     Chriftian
    -0.51
    struzioni
    -0.50
    klart
    -0.50
     navnet
    -0.50
     Determined
    -0.49
    những
    -0.49
    POSITIVE LOGITS
     Wikimedijinoj
    0.93
    期刊论文
    0.68
    addContainerGap
    0.65
     <<<<<<<<<<<<<<
    0.63
     Вікіпе
    0.60
    EnableWeb
    0.58
    حص
    0.56
     Know
    0.53
     pinulongan
    0.53
     समीक्षक
    0.52
    Activations Density 0.070%

    No Known Activations