© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41600
    Prev
    Next
    INDEX
    Explanations

    Thorn

    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
    Chapter
    -0.59
     Costa
    -0.52
    ,
    -0.52
     in
    -0.48
     at
    -0.48
     cut
    -0.48
    chapter
    -0.48
    s
    -0.48
     office
    -0.47
     down
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.96
     يتيمه
    0.92
     الحره
    0.81
    aarrggbb
    0.75
     समीक्षाओं
    0.75
    WebElementEntity
    0.74
     Italijanski
    0.74
     betweenstory
    0.73
     Bioaccumulative
    0.73
     découver
    0.71
    Activations Density 1.383%

    No Known Activations