© 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. 0-RES-MATRYOSHKA-DC
    7. 12058
    Prev
    Next
    INDEX
    Explanations

    references to specific medical procedures and findings, particularly radiotherapy, endoscopic activity, and cartilage

    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
    complexContent
    -0.81
    PerformLayout
    -0.76
     propOrder
    -0.75
    ReusableCell
    -0.74
     disambiguazione
    -0.70
    AsUp
    -0.66
    TestingModule
    -0.65
    ValueStyle
    -0.64
     AssemblyCulture
    -0.63
    UserScript
    -0.63
    POSITIVE LOGITS
    uter
    1.39
    UTER
    0.95
    uters
    0.76
     radiotherapy
    0.72
     AssemblyProduct
    0.63
     infarction
    0.62
     endoscopic
    0.60
     chup
    0.56
     ویکی‌پدیا
    0.56
    migrationBuilder
    0.55
    Activations Density 0.005%

    No Known Activations