© 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. 9054
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions used in complex sentence structures

    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
    tvguidetime
    -0.79
     /\.(
    -0.75
     Мексичка
    -0.74
     محفوظة
    -0.71
    ngdoc
    -0.71
     kasarigan
    -0.71
     revanche
    -0.71
     piede
    -0.70
    Enllaces
    -0.69
    μβρίου
    -0.68
    POSITIVE LOGITS
    ագրություններ
    0.66
    SourceChecksum
    0.61
    참고
    0.55
    Fns
    0.50
    httphttps
    0.49
    LookAnd
    0.49
    anded
    0.47
    EndContext
    0.47
     verbatim
    0.45
    وه
    0.43
    Activations Density 0.187%

    No Known Activations