© 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. 2-RES-MATRYOSHKA-DC
    7. 7701
    Prev
    Next
    INDEX
    Explanations

    instances of the word "escape."

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     secas
    -0.59
    preloader
    -0.54
     Thacker
    -0.53
     meneg
    -0.53
     diber
    -0.52
     sanitaires
    -0.52
    !("{
    -0.51
    ::{
    -0.50
     déploy
    -0.50
     Meadows
    -0.50
    POSITIVE LOGITS
     escape
    3.72
     Escape
    3.31
    escape
    3.30
     escapes
    3.23
    Escape
    3.17
     ESCAPE
    3.02
     escaping
    2.95
     escaped
    2.94
    ESCAPE
    2.47
    escaping
    2.42
    Activations Density 0.020%

    No Known Activations