© 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. 0-RES-MATRYOSHKA-DC
    7. 10728
    Prev
    Next
    INDEX
    Explanations

    mentions of quadratic forms or quadratic expressions in the context of advanced mathematical and physical theories

    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
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.80
    __*/
    -0.76
     Audiodateien
    -0.73
    URLException
    -0.72
     nakalista
    -0.72
    GEBURTSDATUM
    -0.72
     Himo
    -0.71
    
    -0.68
    UpInside
    -0.64
     jScrollPane
    -0.64
    POSITIVE LOGITS
     quadratic
    2.97
     Quadratic
    2.20
    quadratic
    1.95
     quadrat
    0.86
    二次
    0.78
    Quad
    0.66
    openSession
    0.63
     cubic
    0.56
     Off
    0.54
    FirstResponder
    0.53
    Activations Density 0.001%

    No Known Activations