© 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. 30603
    Prev
    Next
    INDEX
    Explanations

    quantitative research-related data points

    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
     abgerufen
    -0.47
    weiler
    -0.46
    ۰۰
    -0.43
    וות
    -0.42
    Nuke
    -0.42
    userdetails
    -0.41
     &
    -0.41
    unan
    -0.41
    ostante
    -0.41
    cious
    -0.41
    POSITIVE LOGITS
     EconPapers
    1.11
     مشين
    0.81
     متعلقه
    0.81
    LookAnd
    0.76
     Efq
    0.76
    migrationBuilder
    0.72
    icitis
    0.70
     ModelExpression
    0.69
     autorytatywna
    0.69
     nahilalakip
    0.69
    Activations Density 0.102%

    No Known Activations