© 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. 252
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections between concepts, particularly using "which" and "that."

    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
    ########.
    -0.42
     enfans
    -0.41
     thêm
    -0.40
    leſs
    -0.40
    assertRaises
    -0.36
     pří
    -0.35
     OMITBAD
    -0.34
     Leandro
    -0.33
     poważ
    -0.32
    odyear
    -0.32
    POSITIVE LOGITS
     which
    1.05
     والتي
    1.00
    which
    0.98
     WHICH
    0.96
     Which
    0.91
     والذي
    0.89
     who
    0.86
    Which
    0.85
    hich
    0.84
     которые
    0.84
    Activations Density 0.945%

    No Known Activations