© 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. 2-RES-MATRYOSHKA-DC
    7. 6383
    Prev
    Next
    INDEX
    Explanations

    mentions of the medical procedure "surgical resection" or similar treatment options

    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
    Personensuche
    -0.88
    consider
    -0.86
    principalTable
    -0.81
     confider
    -0.76
     Consider
    -0.75
    considering
    -0.74
    الإنجليزية
    -0.72
     HasFactory
    -0.72
     plainte
    -0.71
    Ayrıca
    -0.69
    POSITIVE LOGITS
     considered
    1.59
     Considered
    1.41
    considered
    1.33
     deemed
    1.30
     regarded
    1.15
     considerado
    0.98
     dianggap
    0.96
     considerada
    0.94
     consideradas
    0.89
     considerados
    0.86
    Activations Density 0.024%

    No Known Activations