© 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. 9364
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "have" indicating actions or conditions

    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
    s
    -0.66
     lots
    -0.63
    needs
    -0.63
     Capp
    -0.62
    cks
    -0.62
    mits
    -0.61
    sax
    -0.58
     needs
    -0.57
     Moc
    -0.57
    dil
    -0.57
    POSITIVE LOGITS
     themselves
    0.73
    photobucket
    0.69
    protoimpl
    0.68
     ourselves
    0.65
     Rave
    0.65
    verifyException
    0.65
    Twe
    0.65
    peak
    0.64
    otheby
    0.64
    Vendo
    0.64
    Activations Density 0.056%

    No Known Activations