© 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. 21018
    Prev
    Next
    INDEX
    Explanations

    instances of restrictive phrases or clauses involving "of"

    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
     doInBackground
    -1.09
     Efq
    -1.09
    contentLoaded
    -1.02
     houſe
    -0.95
     itſelf
    -0.93
     ſtate
    -0.91
     myſelf
    -0.91
     quæ
    -0.89
     fubject
    -0.89
    StoreMessageInfo
    -0.88
    POSITIVE LOGITS
     McKinnon
    0.68
    o
    0.64
    bery
    0.61
    ie
    0.61
     
    0.61
    ‚¬
    0.60
    ies
    0.59
    stock
    0.58
    וס
    0.54
    <h1>
    0.53
    Activations Density 0.024%

    No Known Activations