© 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. 293
    Prev
    Next
    INDEX
    Explanations

    references to pairs or groups of two in various contexts

    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
     للمعارف
    -0.47
    reicher
    -0.43
     tất
    -0.40
    Specifica
    -0.40
     Photocase
    -0.39
    gemä
    -0.37
    PreInfinity
    -0.37
    GEBURTSDATUM
    -0.37
    dată
    -0.37
    ˾
    -0.37
    POSITIVE LOGITS
     two
    1.03
    two
    0.92
     Beide
    0.84
    Two
    0.82
     deux
    0.82
     TWO
    0.81
     beide
    0.81
    Both
    0.80
     zwei
    0.80
     beiden
    0.79
    Activations Density 2.712%

    No Known Activations