© 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. 31941
    Prev
    Next
    INDEX
    Explanations

    key elements related to cultural and social commentary, particularly focusing on diversity and political contexts

    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
    ViewImports
    -0.50
    haar
    -0.49
    unnitel
    -0.48
     shogun
    -0.48
    Dropout
    -0.46
     Zeitschrift
    -0.46
    unteer
    -0.45
     arra
    -0.45
     suspected
    -0.45
     tắt
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.86
    Przypisy
    0.64
    ----</
    0.58
    Referanser
    0.57
    urlpatterns
    0.54
     surla
    0.53
     spalle
    0.52
    *****/
    0.51
    MeasureSpec
    0.50
    ълга
    0.49
    Activations Density 0.346%

    No Known Activations