© 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. 2846
    Prev
    Next
    INDEX
    Explanations

    references to stress-related traits and responses

    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
     Press
    -1.03
    press
    -1.00
    Press
    -0.99
     PRESS
    -0.99
     press
    -0.96
     presses
    -0.96
     pressed
    -0.93
     pressing
    -0.93
     Pressure
    -0.91
     pressure
    -0.88
    POSITIVE LOGITS
     stress
    2.86
     Stress
    2.61
    Stress
    2.52
    stress
    2.50
     STRESS
    2.36
     stresses
    1.99
     stressed
    1.80
     stres
    1.79
     stressing
    1.73
     estrés
    1.68
    Activations Density 0.010%

    No Known Activations