© 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. 443
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and references to derivatives

    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
    Negative Logits
     beſch
    -0.68
     deſſen
    -0.67
     Dieſe
    -0.66
     wiſſen
    -0.66
     geſch
    -0.66
    <unused23>
    -0.65
     unſer
    -0.65
    <unused8>
    -0.65
    <unused16>
    -0.65
    <pad>
    -0.65
    POSITIVE LOGITS
    2
    0.44
     cuadrado
    0.37
    Jeografia
    0.35
     quadratic
    0.34
     updateTime
    0.34
    sqr
    0.33
     fallu
    0.33
    GeneratedValue
    0.33
     Squared
    0.32
     palace
    0.32
    Activations Density 1.498%

    No Known Activations