© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies, clinical trials, or research collaborations related to cancer, especially focusing on specific cancer types and associated metrics

    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
    Portail
    -0.73
     nakalista
    -0.67
     Paglinawan
    -0.66
    )++;
    -0.66
    InitVars
    -0.65
     typelib
    -0.60
    SharedCtor
    -0.60
     مشين
    -0.59
     Roskov
    -0.59
     Dedicated
    -0.59
    POSITIVE LOGITS
     Cancer
    1.20
    Cancer
    1.02
    Diabetes
    0.85
    Asthma
    0.83
     Asthma
    0.82
     Diabetes
    0.81
     Kidney
    0.78
     Arthritis
    0.78
     Epilepsy
    0.77
    Oste
    0.76
    Activations Density 0.195%

    No Known Activations