© 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. 18-RES-MATRYOSHKA-DC
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    scientific text, especially related to proteins and antigens

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     genome
    -0.75
    Genome
    -0.65
     Genome
    -0.62
     genes
    -0.62
     gene
    -0.58
     genotype
    -0.57
     okuyayım
    -0.56
     epigenetic
    -0.56
     chromosome
    -0.56
     genetic
    -0.55
    POSITIVE LOGITS
     protein
    0.91
     polypep
    0.89
     proteins
    0.88
     Proteins
    0.86
     kDa
    0.83
     polypeptide
    0.81
    protein
    0.78
    Protein
    0.78
     PROTEIN
    0.77
     Protein
    0.77
    Activations Density 1.145%

    No Known Activations