© 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. 408
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
     들어
    -0.41
     blind
    -0.38
    Transparent
    -0.38
     levier
    -0.37
    CHA
    -0.36
    Versions
    -0.36
     weakest
    -0.35
     mode
    -0.35
    Blind
    -0.35
    FormTagHelper
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.53
    verifyException
    0.52
    featureID
    0.47
    SwitchCompat
    0.44
    enterOuterAlt
    0.44
     <<<<<<<<<<<<<<
    0.43
     disambiguazione
    0.43
    modelBuilder
    0.43
     ISNI
    0.43
     considérons
    0.42
    Activations Density 1.329%

    No Known Activations