© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    the word "means."

    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
    ChildScrollView
    -0.77
    ///</
    -0.75
    ThroughAttribute
    -0.75
     يتيمه
    -0.65
     ModelExpression
    -0.56
     typelib
    -0.55
     Lighthouse
    -0.54
     تضيفلها
    -0.54
     gro
    -0.54
    pick
    -0.53
    POSITIVE LOGITS
    Means
    2.97
     Means
    2.95
     means
    2.91
    means
    2.80
     MEANS
    2.72
     mean
    2.56
     MEAN
    2.47
     Mean
    2.44
    MEAN
    2.36
     meaning
    2.23
    Activations Density 0.352%

    No Known Activations