© 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. 3-RES-MATRYOSHKA-DC
    7. 2358
    Prev
    Next
    INDEX
    Explanations

    the start of curly brace-delimited code blocks in a code file

    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
     AssemblyCulture
    -0.76
     ***!
    -0.61
    enterOuterAlt
    -0.57
    ThroughAttribute
    -0.54
    CodeAttribute
    -0.52
    hyrchwyd
    -0.52
    hithe
    -0.52
     transférez
    -0.50
    تقاوى
    -0.50
    aarrggbb
    -0.49
    POSITIVE LOGITS
     StatelessWidget
    0.71
     Shetterly
    0.68
     nasceu
    0.59
    μφωνα
    0.58
    complexType
    0.57
     المعيارى
    0.57
    AccessorTable
    0.56
    INSEE
    0.56
     springfox
    0.55
     rootReducer
    0.54
    Activations Density 0.062%

    No Known Activations