© 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. 1-RES-MATRYOSHKA-DC
    7. 529
    Prev
    Next
    INDEX
    Explanations

    references to a specific software company's name or product, often related to code or development tools

    oai_token-act-pair · gpt-4.1-nano
    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
    脚注の使い方
    -0.67
    gación
    -0.65
     Garn
    -0.59
     Sene
    -0.57
    новниш
    -0.57
    ikiki
    -0.56
     Pali
    -0.56
     autorytatywna
    -0.55
    WebServlet
    -0.54
     atve
    -0.54
    POSITIVE LOGITS
    MS
    3.86
     MS
    3.72
    ms
    3.50
     ms
    3.38
     Ms
    2.41
    Ms
    2.38
     MSD
    1.90
     Microsoft
    1.88
    MSS
    1.79
    Microsoft
    1.67
    Activations Density 0.194%

    No Known Activations