© 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. 20-CLT-HP
    7. 73655
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
    tagext
    -0.59
     '\\;'
    -0.58
    AnchorStyles
    -0.53
     ModelExpression
    -0.49
     Waray
    -0.48
     AspNetCore
    -0.47
     astore
    -0.47
    }');
    -0.46
    URLException
    -0.46
     typelib
    -0.46
    POSITIVE LOGITS
    ưỡng
    0.56
    tagHelper
    0.54
     FRAME
    0.52
     udaler
    0.52
    sell
    0.52
    Out
    0.52
     ude
    0.51
     Bewer
    0.51
    proken
    0.51
    artements
    0.50
    Activations Density 0.001%

    No Known Activations