© 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. 6-RES-MATRYOSHKA-DC
    7. 1393
    Prev
    Next
    INDEX
    Explanations

    mentions of holes in physical objects

    oai_token-act-pair · gemini-2.0-flash
    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
     StatelessWidget
    -0.62
     Palatine
    -0.58
     klock
    -0.56
     TMS
    -0.55
    Bier
    -0.55
     Irrelevant
    -0.54
    Stav
    -0.53
    Ast
    -0.52
     mouseY
    -0.52
     خارجية
    -0.51
    POSITIVE LOGITS
     hole
    1.76
     holes
    1.76
     Holes
    1.68
     HOLE
    1.67
     Hole
    1.66
    Hole
    1.59
    hole
    1.58
    holes
    1.57
    HOLE
    1.50
    Holes
    1.46
    Activations Density 0.716%

    No Known Activations