© 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
    2. Gemma-2-9B
    3. 20-RES-MATRYOSHKA-DC
    4. 39
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or terms related to equations

    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
    expandindo
    -0.63
    AccessorTable
    -0.62
     EconPapers
    -0.61
    __))
    -0.61
    viewDidLoad
    -0.60
     meriva
    -0.59
    OGND
    -0.57
     ſche
    -0.57
    AddTagHelper
    -0.57
    .}}
    -0.57
    POSITIVE LOGITS
    complexContent
    0.42
    帖最后由
    0.41
     and
    0.39
     +
    0.39
     AssemblyVersion
    0.38
     &&
    0.37
     ===
    0.36
    ⓧ
    0.36
     puis
    0.35
     !==
    0.35
    Activations Density 7.761%

    No Known Activations