© 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. 12-RES-MATRYOSHKA-DC
    7. 26098
    Prev
    Next
    INDEX
    Explanations

    terms related to protein epitopes and their determinants

    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
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.78
    tative
    -0.58
    جیب
    -0.58
     szabály
    -0.57
    tory
    -0.57
    ischof
    -0.57
     segü
    -0.57
     lại
    -0.57
     وتسجيلات
    -0.56
     下午
    -0.56
    POSITIVE LOGITS
    itope
    1.52
     epit
    1.27
    Epit
    0.90
     Epit
    0.89
    LabelTagHelper
    0.80
    roek
    0.75
    CreateMap
    0.69
    opes
    0.69
     epithet
    0.68
     Peta
    0.67
    Activations Density 0.001%

    No Known Activations