© 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. 25505
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and symbols typically used in coding or technical writing

    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
     McGu
    -0.63
     Gather
    -0.62
     Prieto
    -0.61
     Tric
    -0.60
     Frat
    -0.60
    kof
    -0.60
    colage
    -0.58
     Aplica
    -0.57
    Gather
    -0.55
     Azt
    -0.55
    POSITIVE LOGITS
    RepeatedField
    0.74
    ніципалі
    0.73
    ollectionView
    0.72
     mergeFrom
    0.70
    Personendaten
    0.67
     --}}
    0.65
     HttpHeaders
    0.63
    endpush
    0.61
    سرائيلي
    0.61
    Dichloropropane
    0.60
    Activations Density 0.087%

    No Known Activations