© 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. 6-RES-MATRYOSHKA-DC
    7. 430
    Prev
    Next
    INDEX
    Explanations

    text related to cancer research

    oai_token-act-pair · gemini-2.0-flash
    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
     مرئيه
    -0.73
    出版年
    -0.64
    }());
    -0.61
     Audiodateien
    -0.60
     "'",
    -0.60
    ayla
    -0.60
    ódó
    -0.59
    ifolia
    -0.56
     Kew
    -0.55
    
    -0.55
    POSITIVE LOGITS
     cancer
    1.83
     Cancer
    1.70
     CANCER
    1.66
    Cancer
    1.65
     cancers
    1.58
    cancer
    1.57
     tumor
    1.53
     tumors
    1.50
     tumour
    1.48
     cancerous
    1.45
    Activations Density 1.461%

    No Known Activations