© 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. 4309
    Prev
    Next
    INDEX
    Explanations

    references to medical and radiological guidelines and practices

    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
     Civil
    -0.85
    Civil
    -0.84
     civil
    -0.78
    civil
    -0.74
     CIVIL
    -0.65
     civile
    -0.64
     humains
    -0.59
     hâte
    -0.58
     civili
    -0.55
     umani
    -0.55
    POSITIVE LOGITS
    CIT
    3.22
     CIT
    2.66
    cit
    2.27
     Cit
    2.17
    Cit
    2.13
     cit
    2.03
     citrate
    1.07
     Citron
    0.97
    cita
    0.96
     citi
    0.96
    Activations Density 0.004%

    No Known Activations