© 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. 15861
    Prev
    Next
    INDEX
    Explanations

    occurrences of the apostrophe followed by the letter "s"

    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
     getItemCount
    -0.69
    StoryboardSegue
    -0.63
     découver
    -0.62
    roek
    -0.62
     judiciales
    -0.60
     Roskov
    -0.60
     transfé
    -0.60
     XMLHttpRequest
    -0.59
     ModelExpression
    -0.59
    principalTable
    -0.59
    POSITIVE LOGITS
     autorytatywna
    0.70
    EndInit
    0.60
    aarrggbb
    0.60
    KommentareTeilen
    0.57
     refere
    0.56
    +"'
    0.56
    ›
    0.56
    AddTagHelper
    0.56
    SharedDtor
    0.54
    postIndex
    0.52
    Activations Density 0.006%

    No Known Activations