© 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. 0-RES-MATRYOSHKA-DC
    7. 13218
    Prev
    Next
    INDEX
    Explanations

    references to a specific immune cell type involved in inflammation and immune responses

    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
     InputDecoration
    -0.91
    AndEndTag
    -0.86
    TagHelper
    -0.79
    CPtr
    -0.75
    ArrowToggle
    -0.72
     BoxDecoration
    -0.71
    MessageOf
    -0.68
    IntoConstraints
    -0.67
    InvalidProtocol
    -0.66
    elemField
    -0.66
    POSITIVE LOGITS
     lympho
    3.59
     Lympho
    1.87
    Lymp
    0.90
     lymp
    0.70
    lymp
    0.61
     lymphocyte
    0.56
     leak
    0.52
     Leak
    0.50
     шо
    0.50
     Llew
    0.49
    Activations Density 0.000%

    No Known Activations