© 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. 6772
    Prev
    Next
    INDEX
    Explanations

    references to genes and their expressions

    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
    SpringBootTest
    -0.78
    acruz
    -0.69
    sembly
    -0.68
    visionnement
    -0.66
    igth
    -0.65
    openqa
    -0.65
     Rotterdam
    -0.62
    kolwiek
    -0.62
    koła
    -0.62
    fxml
    -0.61
    POSITIVE LOGITS
     Genes
    1.02
    genes
    1.00
     genes
    0.99
     GENE
    0.95
    GENE
    0.91
    Genes
    0.90
    gene
    0.87
     Gene
    0.87
    Gene
    0.83
     gene
    0.76
    Activations Density 0.047%

    No Known Activations