© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    mentions of medical procedures or interventions involving surgical or endovascular techniques

    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
    AndEndTag
    -0.57
     rasp
    -0.54
    ritation
    -0.54
     vych
    -0.50
    wikimedia
    -0.50
     isInitialized
    -0.50
     ARISING
    -0.49
    diyah
    -0.46
    SequentialGroup
    -0.46
     gez
    -0.46
    POSITIVE LOGITS
     underwent
    2.81
     undergo
    2.80
     undergoes
    2.72
     undergone
    2.63
     undergoing
    2.47
     menjalani
    1.10
     sufre
    0.97
    دانشنامهٔ
    0.92
     sufrió
    0.91
     mengalami
    0.90
    Activations Density 0.004%

    No Known Activations