© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    the term "usage" or "Usage" in code and documentation files

    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
    élection
    -0.81
    IUrlHelper
    -0.75
     Geraadpleegd
    -0.75
     rhestr
    -0.74
    ValueStyle
    -0.73
     DeL
    -0.70
     morire
    -0.69
    Билгалдахарш
    -0.69
     DeWitt
    -0.69
     Seel
    -0.68
    POSITIVE LOGITS
     Usage
    2.33
     usage
    2.28
    Usage
    2.28
    usage
    2.11
    USAGE
    2.02
     USAGE
    1.88
     usages
    1.61
    usages
    1.40
     consumption
    0.95
     Nutzungs
    0.87
    Activations Density 0.017%

    No Known Activations