© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7371
    Prev
    Next
    INDEX
    Explanations

    references to specific immune cell types involved in innate immunity, particularly monocytes and macrophages

    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
     تضيفلها
    -0.86
     مشين
    -0.85
     NSCoder
    -0.82
     myſelf
    -0.79
    NUMX
    -0.77
    principalColumn
    -0.77
     ويكيپيديا
    -0.76
    CPtr
    -0.76
    tonsoft
    -0.75
    Rohy
    -0.75
    POSITIVE LOGITS
     macrophages
    2.83
     macrophage
    2.17
    hages
    1.60
     monocytes
    1.16
     phag
    0.79
    hage
    0.64
     fibroblasts
    0.59
     neutrophils
    0.57
     fibroblast
    0.56
    venger
    0.55
    Activations Density 0.004%

    No Known Activations