© 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. 425
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables that are defined or manipulated

    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
    MessageTagHelper
    -0.42
     <<<<<<<<<<<<<<
    -0.41
    TextUtils
    -0.40
     backwards
    -0.40
    AnimationsModule
    -0.39
     policial
    -0.39
    contentPane
    -0.37
     Darm
    -0.37
     mCurrent
    -0.37
     prou
    -0.36
    POSITIVE LOGITS
     Let
    0.73
    Let
    0.66
     Lett
    0.66
     let
    0.59
     LET
    0.58
     propOrder
    0.58
    Lett
    0.57
    rungsseite
    0.57
     ligiloj
    0.56
    LookAnd
    0.55
    Activations Density 0.298%

    No Known Activations