© 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. 3-RES-MATRYOSHKA-DC
    7. 506
    Prev
    Next
    INDEX
    Explanations

    mentions of CD8+ T cells and immunology research studies

    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
    3
    -0.81
     Kome
    -0.78
    ichel
    -0.77
    meida
    -0.73
    Samoa
    -0.73
     الثلاث
    -0.72
     Tig
    -0.71
     CMP
    -0.71
     Brind
    -0.71
    ịp
    -0.69
    POSITIVE LOGITS
    8
    1.57
     EIGHT
    1.55
     eight
    1.48
     Eighth
    1.45
     Eight
    1.43
     eighth
    1.36
     VIII
    1.34
     huit
    1.34
    eight
    1.34
    Eight
    1.30
    Activations Density 2.928%

    No Known Activations