© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    instances of the word "command" in code or technical contexts

    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
     المعيارى
    -0.73
     Bathurst
    -0.67
    Hansen
    -0.63
     fó
    -0.61
     Haram
    -0.60
     Uniti
    -0.60
     PCP
    -0.57
     Lagi
    -0.57
    Sera
    -0.57
    بوابة
    -0.56
    POSITIVE LOGITS
     command
    2.84
     Command
    2.81
     COMMAND
    2.64
    command
    2.59
    Command
    2.58
     commands
    2.56
     Commands
    2.42
    commands
    2.41
    COMMAND
    2.36
    Commands
    2.17
    Activations Density 0.130%

    No Known Activations