© 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. 286
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and indexing used in formal proofs or algorithms

    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
    OGND
    -0.69
    StructEnd
    -0.52
    FormTagHelper
    -0.51
     BrowserModule
    -0.48
    хьтан
    -0.47
     שוליים
    -0.47
    posedge
    -0.46
     Wikiseite
    -0.44
    MenuInflater
    -0.44
    viewDidLoad
    -0.43
    POSITIVE LOGITS
    Each
    0.73
     each
    0.71
     Each
    0.68
    each
    0.62
     individually
    0.59
    Chaque
    0.58
     Каждый
    0.57
     bawat
    0.56
    每一次
    0.55
    Каждый
    0.55
    Activations Density 3.580%

    No Known Activations