© 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. 30658
    Prev
    Next
    INDEX
    Explanations

    references to recombinant proteins

    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
    ridae
    -0.78
    mybatisplus
    -0.77
     &'
    -0.65
    PageModule
    -0.65
    zzlies
    -0.64
     krat
    -0.64
     Senna
    -0.63
    apad
    -0.63
    agrid
    -0.61
     Matilda
    -0.60
    POSITIVE LOGITS
    binant
    1.63
     recombinant
    1.00
     recombination
    1.00
    recom
    0.96
     recom
    0.90
    Recom
    0.87
     Recom
    0.86
    bination
    0.84
     RECOM
    0.81
    unhofer
    0.77
    Activations Density 0.003%

    No Known Activations