© 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. 7268
    Prev
    Next
    INDEX
    Explanations

    references to the action of pressing a button or key

    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
     stress
    -0.97
    Stress
    -0.93
     Stress
    -0.92
     STRESS
    -0.75
     Pressure
    -0.73
    Pressure
    -0.73
     pressure
    -0.71
    stress
    -0.71
     tension
    -0.68
     stres
    -0.68
    POSITIVE LOGITS
     press
    2.84
    press
    2.55
    Press
    2.52
     Press
    2.47
     PRESS
    2.42
     presses
    2.31
     pressed
    1.99
     pressing
    1.93
     Pressing
    1.87
    pressing
    1.83
    Activations Density 0.016%

    No Known Activations