© 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. 1-RES-MATRYOSHKA-DC
    7. 458
    Prev
    Next
    INDEX
    Explanations

    references to specific annotated medical or surgical procedures and anatomical features

    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
    gameserver
    -0.77
     rapporti
    -0.75
     étrangère
    -0.72
     AppModule
    -0.72
    openzeppelin
    -0.71
    MethodManager
    -0.70
     Goodreads
    -0.69
     ViewPager
    -0.69
     cellulare
    -0.69
     REA
    -0.69
    POSITIVE LOGITS
     utilising
    1.09
     optimised
    1.02
     iconic
    0.98
     util
    0.96
     utilizing
    0.94
     leveraging
    0.94
    Utiliz
    0.93
     via
    0.93
     optimisation
    0.93
    Into
    0.92
    Activations Density 10.171%

    No Known Activations