© 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. 25244
    Prev
    Next
    INDEX
    Explanations

    keywords and names related to science and gene-related work

    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
     跳转至
    -0.63
    localctx
    -0.61
    łość
    -0.53
    idł
    -0.51
     temperance
    -0.50
    icitis
    -0.50
    sizeCache
    -0.50
     متعلقه
    -0.50
    AutoField
    -0.49
    บาล
    -0.49
    POSITIVE LOGITS
    '")
    0.57
    исленность
    0.56
     Процитовано
    0.56
    __["
    0.55
    portál
    0.55
    Known
    0.50
     Known
    0.50
    dic
    0.50
     famously
    0.49
     SAB
    0.49
    Activations Density 0.909%

    No Known Activations