© 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. 3433
    Prev
    Next
    INDEX
    Explanations

    specific code-related patterns and instructions in technical documents

    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
    ValueStyle
    -0.59
    mayr
    -0.58
    pnea
    -0.58
    GeneratedCode
    -0.57
     EClass
    -0.57
     <=",
    -0.56
    élien
    -0.54
    NewUrlParser
    -0.53
    IContainer
    -0.52
     nahilalakip
    -0.52
    POSITIVE LOGITS
    StoryboardSegue
    0.65
     InputDecoration
    0.59
     StatefulWidget
    0.56
     Wann
    0.50
     BoxDecoration
    0.49
    ">:
    0.49
    Extremely
    0.49
     LoggerFactory
    0.47
     Extremely
    0.47
     "");
    0.47
    Activations Density 5.691%

    No Known Activations