© 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. 206
    Prev
    Next
    INDEX
    Explanations

    mentions of discovering or determining something through analysis or investigation

    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
    ApiOperation
    -0.62
    invokeLater
    -0.60
    MeasureSpec
    -0.57
    EndInit
    -0.56
    ImageContext
    -0.54
    ReusableCell
    -0.54
    ContentAsync
    -0.53
    CreateModel
    -0.52
    putAll
    -0.52
    nloa
    -0.52
    POSITIVE LOGITS
     found
    3.83
     find
    3.69
     finds
    3.56
    find
    3.47
     finding
    3.45
     FIND
    3.41
     Found
    3.38
     Find
    3.31
    found
    3.31
    Find
    3.28
    Activations Density 0.587%

    No Known Activations