© 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. 23364
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and high-dimensional spaces in text

    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
     protoimpl
    -1.30
    awtextra
    -1.27
     للاسماء
    -1.20
    PreferredItem
    -1.16
     ModelExpression
    -1.16
     Савезне
    -1.11
     ProtoMessage
    -1.11
    клопе
    -1.09
     Monfieur
    -1.09
    AccessorTable
    -1.09
    POSITIVE LOGITS
     
    0.51
     des
    0.46
    ↵↵
    0.45
    ,
    0.45
     and
    0.43
     au
    0.41
     (
    0.40
     still
    0.40
    —
    0.39
    .
    0.39
    Activations Density 0.000%

    No Known Activations