© 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. 4998
    Prev
    Next
    INDEX
    Explanations

    references to exercise therapy or programs

    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
    rrggbb
    -0.90
     betweenstory
    -0.82
     CreateTagHelper
    -0.81
    tagHelperRunner
    -0.73
    IntoConstraints
    -0.72
    outSlope
    -0.71
    duled
    -0.70
    UnusedPrivate
    -0.70
    pertise
    -0.69
     EconPapers
    -0.69
    POSITIVE LOGITS
     exercise
    3.56
     Exercise
    3.17
    Exercise
    3.08
    exercise
    3.03
     EXERCISE
    2.89
     exercises
    2.67
     exercising
    2.67
     exercised
    2.59
    EXERCISE
    2.47
     Exercises
    2.36
    Activations Density 0.029%

    No Known Activations