© 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. 1136
    Prev
    Next
    INDEX
    Explanations

    references to configuration files or settings

    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
    xrTableCell
    -0.60
     onCreateView
    -0.57
     ExecuteAsync
    -0.57
     yyj
    -0.56
     CWE
    -0.55
    例句
    -0.55
     Nani
    -0.55
    Kontrola
    -0.54
     ControllerBase
    -0.54
     QLabel
    -0.53
    POSITIVE LOGITS
     config
    3.80
    config
    3.67
     Config
    3.47
     configuration
    3.42
    Config
    3.31
     Configuration
    3.27
    CONFIG
    2.98
    configuration
    2.97
     CONFIG
    2.95
    Configuration
    2.92
    Activations Density 0.202%

    No Known Activations