© 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. 1687
    Prev
    Next
    INDEX
    Explanations

    code related to software modules in several programming languages

    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
     defStyleAttr
    -0.67
    NameInMap
    -0.64
    migrationBuilder
    -0.64
    Ona
    -0.63
     Krus
    -0.63
     Bellow
    -0.63
    kungen
    -0.62
    ็จ
    -0.62
    ibatis
    -0.62
     PICT
    -0.61
    POSITIVE LOGITS
    module
    3.03
     module
    2.97
     modules
    2.97
     Module
    2.86
     Modules
    2.83
    Module
    2.73
    modules
    2.69
    Modules
    2.55
     MODULE
    2.52
    MODULE
    2.28
    Activations Density 0.129%

    No Known Activations