© 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. 0-RES-MATRYOSHKA-DC
    7. 10605
    Prev
    Next
    INDEX
    Explanations

    references to immunoglobulins, specifically immunoglobulin classes such as IgA, IgE, IgG, and IgM

    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
    Negative Logits
     незавершена
    -0.63
    رشف
    -0.60
     Infórmanos
    -0.57
    ⓧ
    -0.54
     Exacts
    -0.53
    bottomRight
    -0.53
    TintMode
    -0.51
     ră
    -0.48
    Распо
    -0.47
    CPtr
    -0.47
    POSITIVE LOGITS
     Hb
    1.60
    Hb
    1.09
    oglobin
    1.00
    oglobulin
    0.81
    oglo
    0.75
    /**
    0.75
     CreateTagHelper
    0.72
     immunoglobulin
    0.72
    mobileqq
    0.68
    +#+
    0.66
    Activations Density 0.001%

    No Known Activations