© 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. 23518
    Prev
    Next
    INDEX
    Explanations

    expressions related to causation or influence

    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
     raiſ
    -0.68
     itſelf
    -0.66
     Zd
    -0.64
    IsContent
    -0.62
     Wraith
    -0.61
     Scin
    -0.60
    onekana
    -0.60
     Quint
    -0.60
     autorytatywna
    -0.60
     drives
    -0.58
    POSITIVE LOGITS
     scolaires
    0.67
    SequentialGroup
    0.65
     оригіналу
    0.62
    γγε
    0.60
    ebvre
    0.58
     hohem
    0.57
    PreferredItem
    0.56
    CopyWith
    0.55
     lehetős
    0.54
     religieuses
    0.54
    Activations Density 0.079%

    No Known Activations