© 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. 3-RES-MATRYOSHKA-DC
    7. 3199
    Prev
    Next
    INDEX
    Explanations

    the word "promise" (or "promises") followed by a preposition or as part of a class or function named Promise

    oai_token-act-pair · gemini-2.0-flash
    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
     indisponible
    -0.63
     Hayek
    -0.59
    lück
    -0.57
     Auff
    -0.53
     indirectly
    -0.52
    Nef
    -0.52
     AllMovie
    -0.51
    cination
    -0.50
     Auteur
    -0.50
     AspNetCore
    -0.50
    POSITIVE LOGITS
     promise
    3.31
     Promise
    3.13
     promises
    2.94
    promise
    2.91
    Promise
    2.86
     Promises
    2.66
     promised
    2.61
    promises
    2.56
     promesa
    2.50
     promis
    2.47
    Activations Density 0.019%

    No Known Activations