© 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. 3-RES-MATRYOSHKA-DC
    7. 1255
    Prev
    Next
    INDEX
    Explanations

    curly braces containing labels for equations in LaTeX documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {#
    -0.59
     #
    -0.49
     tér
    -0.44
    <%@
    -0.44
    ANNES
    -0.42
     Naked
    -0.41
     
    -0.41
    fml
    -0.41
    mantec
    -0.40
    CEED
    -0.40
    POSITIVE LOGITS
    DoubleQuotes
    0.94
     propOrder
    0.91
    новниш
    0.79
    LookAnd
    0.79
    aarrggbb
    0.78
     */
    0.76
     Italijani
    0.76
    MessageTagHelper
    0.74
    */
    0.74
    uidado
    0.72
    Activations Density 0.197%

    No Known Activations