© 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-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7706
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tie" and related tie-related terms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    AccessorTable
    -0.66
    Tikang
    -0.64
    tilli
    -0.61
    mäß
    -0.58
    Vidite
    -0.57
     Zeng
    -0.57
     TEMPLATE
    -0.57
    postmedia
    -0.56
    `]
    -0.56
    addPreferredGap
    -0.55
    POSITIVE LOGITS
     tie
    3.33
     tied
    2.91
     ties
    2.91
     Tie
    2.78
     tying
    2.78
    Tie
    2.66
     Ties
    2.66
     Tied
    2.45
    Tied
    2.39
     TIE
    2.22
    Activations Density 0.009%

    No Known Activations