© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15787
    Prev
    Next
    INDEX
    Explanations

    references to specific canal structures in the body

    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
    felf
    -0.47
    ament
    -0.44
    NSON
    -0.44
     ATP
    -0.43
     inhoud
    -0.42
     Sander
    -0.42
     pod
    -0.42
     ít
    -0.41
    caras
    -0.41
    xodo
    -0.41
    POSITIVE LOGITS
    stin
    1.06
    heal
    0.95
     heal
    0.93
    expandindo
    0.93
     defaultstate
    0.91
     muco
    0.91
    aarrggbb
    0.90
     المعيارى
    0.85
    awtextra
    0.81
     graze
    0.81
    Activations Density 0.015%

    No Known Activations