© 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. 31806
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements in the 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
    aarrggbb
    -0.55
     fuite
    -0.54
    GEBURTSDATUM
    -0.52
    client
    -0.51
    msgSender
    -0.50
    Client
    -0.49
     giản
    -0.49
    adpleegd
    -0.49
    DEAL
    -0.47
    calaureate
    -0.47
    POSITIVE LOGITS
     lenker
    0.64
    ScopeManager
    0.64
    kloped
    0.61
     ✭✭
    0.60
     HasFactory
    0.59
    AddAttribute
    0.58
     semej
    0.57
    TagMode
    0.57
     bahay
    0.57
    ([...
    0.57
    Activations Density 0.001%

    No Known Activations