© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5439
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as script tags, function definitions, and change event handlers

    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
     wait
    -0.45
     stof
    -0.44
    wait
    -0.44
    ampilan
    -0.44
     abond
    -0.44
    rowad
    -0.43
    ]=-
    -0.43
    ctory
    -0.43
     présent
    -0.43
    qrstuvwxyz
    -0.43
    POSITIVE LOGITS
     MotionEvent
    1.13
    UpInside
    1.06
     mouseClicked
    1.04
     actionPerformed
    1.02
    TextWatcher
    1.02
    onActivityResult
    0.98
     EventArgs
    0.95
    ActionPerformed
    0.94
    StoryboardSegue
    0.94
     eventdata
    0.93
    Activations Density 0.559%

    No Known Activations