© 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. 18758
    Prev
    Next
    INDEX
    Explanations

    references to genomic sequencing and mutation analysis technologies

    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
    хьтан
    -0.50
     Feed
    -0.48
    期刊论文
    -0.48
    arko
    -0.47
    стам
    -0.46
     trying
    -0.46
    feed
    -0.45
    Feed
    -0.45
    fir
    -0.45
     Sie
    -0.44
    POSITIVE LOGITS
     ſtate
    0.95
     houſe
    0.95
     Majefty
    0.94
     Efq
    0.93
    AddTagHelper
    0.90
     Houſe
    0.89
     itſelf
    0.89
     pleaſure
    0.87
     Conſ
    0.84
     Diſ
    0.84
    Activations Density 0.134%

    No Known Activations