© 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. 1-RES-MATRYOSHKA-DC
    7. 597
    Prev
    Next
    INDEX
    Explanations

    references to quantities or degrees that are close to but just less than a full or maximum value

    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
    alej
    -0.75
    InitVars
    -0.65
    endesk
    -0.61
     Tampoco
    -0.57
    ItemBackground
    -0.57
     ferner
    -0.56
     ayrıca
    -0.56
     myſelf
    -0.56
    ckså
    -0.54
    featureID
    -0.54
    POSITIVE LOGITS
     almost
    3.94
     nearly
    3.91
    almost
    3.81
    Almost
    3.78
     Almost
    3.73
    nearly
    3.70
     Nearly
    3.56
    Nearly
    3.48
     quase
    2.98
     bijna
    2.89
    Activations Density 0.218%

    No Known Activations