© 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. 6849
    Prev
    Next
    INDEX
    Explanations

    references to activities involving rapid or continuous movement

    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
    run
    -1.10
     run
    -1.02
    Run
    -0.82
     Run
    -0.78
     RUN
    -0.58
    PMailer
    -0.57
     تضيفلها
    -0.56
    ⓧ
    -0.56
     meninos
    -0.56
    MessageOf
    -0.54
    POSITIVE LOGITS
     running
    2.47
     Running
    2.28
    Running
    2.23
    running
    2.17
     RUNNING
    2.08
    RUNNING
    1.79
     corriendo
    0.87
    isRunning
    0.83
     flowing
    0.82
     jogging
    0.81
    Activations Density 0.013%

    No Known Activations