© 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. 12-RES-MATRYOSHKA-DC
    7. 32560
    Prev
    Next
    INDEX
    Explanations

    mentions of antigens in the context of immunological discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ništvo
    -0.89
    ніципалі
    -0.85
    httphttps
    -0.84
    writeHead
    -0.82
    Архівовано
    -0.81
    NameInMap
    -0.81
     Talley
    -0.79
     CiNii
    -0.78
    RenderAtEndOf
    -0.76
    RTLD
    -0.75
    POSITIVE LOGITS
     antigen
    1.22
     antigens
    1.21
     Antigen
    1.05
     Antig
    0.86
    tigen
    0.73
     Rober
    0.71
     Ogle
    0.66
    igens
    0.65
    stig
    0.65
     Merz
    0.64
    Activations Density 0.006%

    No Known Activations