© 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. 31293
    Prev
    Next
    INDEX
    Explanations

    universal or inclusive terms that indicate all instances or measurements

    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
     attore
    -0.52
     coté
    -0.51
     hivat
    -0.51
     Sociale
    -0.48
     تانيه
    -0.48
     bepaalde
    -0.48
    attore
    -0.48
     convento
    -0.47
    intéress
    -0.47
    fseek
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.61
     doInBackground
    0.60
     yii
    0.58
    ReusableCell
    0.58
    webElementXpaths
    0.57
    IsPostBack
    0.57
    ement
    0.56
    testng
    0.56
     AutoMapper
    0.56
    fillType
    0.55
    Activations Density 0.035%

    No Known Activations