© 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. 3-RES-MATRYOSHKA-DC
    7. 1878
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "run", often in relation to code or some process being run

    oai_token-act-pair · gemini-2.0-flash
    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
     myſelf
    -0.89
     purpoſe
    -0.89
    ⓧ
    -0.81
     ſtate
    -0.80
     pleaſure
    -0.80
     houſe
    -0.79
     themſelves
    -0.79
     ſch
    -0.77
     ſeveral
    -0.77
     cauſe
    -0.77
    POSITIVE LOGITS
     run
    3.36
     Run
    3.13
    Run
    2.95
    run
    2.92
     runs
    2.88
     RUN
    2.80
     Runs
    2.67
    RUN
    2.64
     running
    2.59
    runs
    2.55
    Activations Density 0.366%

    No Known Activations