© 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. 12415
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures involving cannulation

    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
     isolado
    -0.59
    toMatchSnapshot
    -0.57
    Isolated
    -0.57
    PathVariable
    -0.52
     FormBuilder
    -0.51
    かわらず
    -0.50
     gereken
    -0.50
     Isolated
    -0.50
    localtime
    -0.49
     Gould
    -0.49
    POSITIVE LOGITS
     cann
    1.24
     congru
    1.18
     congruence
    1.17
     congruent
    1.15
     permissible
    0.92
    Berger
    0.90
     Berger
    0.87
    GGT
    0.84
     Jessica
    0.75
     berger
    0.73
    Activations Density 0.003%

    No Known Activations