© 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. 1-RES-MATRYOSHKA-DC
    7. 971
    Prev
    Next
    INDEX
    Explanations

    references to immune responses or immunological processes

    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
    ParallelGroup
    -0.66
     cinematogra
    -0.64
    AddTagHelper
    -0.63
    principalTable
    -0.63
    centralwidget
    -0.60
     barge
    -0.58
    fillType
    -0.58
     Cane
    -0.57
     ciné
    -0.56
    Cane
    -0.56
    POSITIVE LOGITS
     immun
    3.53
     immune
    3.22
     Immun
    3.22
    immun
    3.19
    Immun
    3.11
     Immune
    2.98
     inmun
    2.98
     immunity
    2.80
    immune
    2.77
     immunological
    2.70
    Activations Density 1.139%

    No Known Activations