© 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. 14944
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation marks

    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
    transQ
    -0.62
    thorax
    -0.48
    elemField
    -0.46
     BMS
    -0.44
    farin
    -0.44
     Lazio
    -0.43
    oleum
    -0.41
    WhereInput
    -0.40
     Lexer
    -0.40
    Compose
    -0.39
    POSITIVE LOGITS
    TagMode
    0.88
    Hochspringen
    0.76
     "..\..\
    0.74
    mybatisplus
    0.74
     "..\..\..\
    0.73
    WireFormatLite
    0.72
    omenclature
    0.71
    rungsseite
    0.70
    Tarih
    0.68
    ӳ
    0.67
    Activations Density 0.001%

    No Known Activations