© 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. 215
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
    transQ
    -0.71
     Efq
    -0.64
    Clik
    -0.62
     IBOutlet
    -0.61
     Normdatei
    -0.60
    webElement
    -0.60
    exitRule
    -0.60
    thâu
    -0.60
    Попис
    -0.59
     Jove
    -0.57
    POSITIVE LOGITS
     nemlig
    0.42
     indépendante
    0.42
     définiti
    0.41
     ľud
    0.41
     homenagem
    0.41
     rodillas
    0.41
    hilangan
    0.40
     Apart
    0.40
     verksam
    0.40
    <eos>
    0.40
    Activations Density 1.499%

    No Known Activations