© 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. 442
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their definitions

    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
    ülé
    -0.42
     ✭✭
    -0.41
     onCreateView
    -0.40
    bied
    -0.38
     asyncio
    -0.38
     ttk
    -0.37
    latego
    -0.37
     Erscheinung
    -0.37
    ::_('
    -0.36
    *///
    -0.35
    POSITIVE LOGITS
    VersionUID
    0.49
    ̈́
    0.46
    AndEndTag
    0.45
    ValueStyle
    0.44
    parsedMessage
    0.43
     Савезне
    0.42
    RTEX
    0.42
     Presumably
    0.42
     '\\;'
    0.41
     refers
    0.41
    Activations Density 2.506%

    No Known Activations