© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 64
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical concepts related to advanced theoretical physics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     queſta
    -0.71
    +#+
    -0.71
    ſelf
    -0.70
    ьаж
    -0.70
     houſe
    -0.67
    Ꞓ
    -0.66
     fusca
    -0.65
    UVWXYZ
    -0.65
     pleaſure
    -0.65
     IBOutlet
    -0.65
    POSITIVE LOGITS
     model
    0.52
     analysis
    0.47
     $\
    0.46
     structure
    0.45
     theory
    0.43
     Theorie
    0.43
     $
    0.42
     analogous
    0.42
     mode
    0.40
     řešení
    0.39
    Activations Density 13.642%

    No Known Activations