© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12771
    Prev
    Next
    INDEX
    Explanations

    mentions of procedures involving limb reconstruction and limb salvage surgery

    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
     debo
    -0.54
     put
    -0.48
     взя
    -0.47
     lit
    -0.43
     found
    -0.43
     kept
    -0.43
     noticed
    -0.42
    abou
    -0.41
    illez
    -0.41
     
    -0.41
    POSITIVE LOGITS
     consisted
    1.27
     depended
    1.06
     belonged
    1.03
     differed
    0.98
    SerializedSize
    0.91
    Према
    0.90
    WithIOException
    0.87
    ReusableCell
    0.85
    saraba
    0.84
     transfieras
    0.83
    Activations Density 0.030%

    No Known Activations