© 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. 200
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and specifications in a scientific context

    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
    NamedQueries
    -0.33
     festas
    -0.29
    BIÉN
    -0.28
     cappello
    -0.28
     roulant
    -0.28
     bordes
    -0.28
    SharedCtor
    -0.27
     dureza
    -0.27
     zvlá
    -0.26
    statusText
    -0.26
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     AssemblyCompany
    0.79
    GOTREF
    0.73
    AddTagHelper
    0.71
    Parcelize
    0.65
     Shakspeare
    0.65
    
    0.65
     arşivlendi
    0.64
     Monfieur
    0.64
    ſelves
    0.63
    Activations Density 3.092%

    No Known Activations