© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    references to military entities or groups involved in conflict

    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
    stretchr
    -0.54
    endpush
    -0.53
     reação
    -0.52
     cópia
    -0.50
     Christianity
    -0.50
    gorov
    -0.50
    SEGUIR
    -0.49
    StreetMap
    -0.49
    }}</
    -0.49
    󠁢
    -0.48
    POSITIVE LOGITS
    vician
    0.66
    Rüyada
    0.63
    δή
    0.63
    はじめに
    0.56
     BorderSide
    0.56
     Guth
    0.52
    Portail
    0.51
    Indented
    0.50
     postIndex
    0.50
    memoized
    0.49
    Activations Density 0.016%

    No Known Activations