© 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. 6781
    Prev
    Next
    INDEX
    Explanations

    lines or code snippets containing the keyword related to "operation" or "operator."

    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
     eyes
    -0.73
    eyes
    -0.69
    printStackTrace
    -0.65
    xase
    -0.63
    EYE
    -0.63
    ţilor
    -0.63
     Ooster
    -0.63
     Eye
    -0.62
     Eyes
    -0.60
    Eyes
    -0.59
    POSITIVE LOGITS
    op
    3.23
     op
    2.94
    OP
    2.72
    Op
    2.56
     Op
    2.55
     OP
    2.42
    ops
    1.45
    opse
    1.34
     оп
    1.30
    oped
    1.29
    Activations Density 0.089%

    No Known Activations