© 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. 429
    Prev
    Next
    INDEX
    Explanations

    keywords related to flower delivery services and their promotional offerings

    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
     iirc
    -0.56
     unsuccessfully
    -0.55
     apparently
    -0.54
    apparently
    -0.53
    Apparently
    -0.53
     unsuccessful
    -0.52
    一応
    -0.51
     partly
    -0.49
     putative
    -0.48
     presumably
    -0.48
    POSITIVE LOGITS
     pleaſure
    0.66
     your
    0.65
    guar
    0.60
     houſe
    0.59
    your
    0.59
     GUARANTE
    0.58
    professionals
    0.57
     YOUR
    0.57
    为您
    0.56
     enjoy
    0.54
    Activations Density 3.591%

    No Known Activations