© 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. 2-RES-MATRYOSHKA-DC
    7. 5787
    Prev
    Next
    INDEX
    Explanations

    references to legal or procedural process

    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
    \{\\
    -0.66
    reportWebVitals
    -0.65
    MemoryWarning
    -0.64
    AddHtmlAttribute
    -0.60
    tersebut
    -0.57
    WebVitals
    -0.57
     StatefulWidget
    -0.56
    eseorang
    -0.55
     XCTest
    -0.55
    ServletException
    -0.55
    POSITIVE LOGITS
     process
    0.79
    process
    0.79
    Process
    0.76
     Process
    0.74
     PROCESS
    0.62
     proceso
    0.59
    PROCESS
    0.59
    libft
    0.58
     fanfare
    0.58
    Kort
    0.55
    Activations Density 0.019%

    No Known Activations