© 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. 15807
    Prev
    Next
    INDEX
    Explanations

    references to figures or data visualizations

    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
     فريبيس
    -0.93
    
    -0.91
     ComVisible
    -0.90
    MigrationBuilder
    -0.88
    Personensuche
    -0.88
    GeoNames
    -0.81
    Gambas
    -0.75
     Gibbon
    -0.72
    TabStop
    -0.70
    richTextPanel
    -0.69
    POSITIVE LOGITS
    leştir
    0.51
     bedeckt
    0.49
    στι
    0.48
    createCanvas
    0.47
     Süß
    0.47
    ptures
    0.47
    重
    0.47
    ächst
    0.45
    ępnie
    0.45
    tures
    0.45
    Activations Density 0.008%

    No Known Activations