© 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. 6-RES-MATRYOSHKA-DC
    7. 1403
    Prev
    Next
    INDEX
    Explanations

    the word "predict" or variations.

    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
    weile
    -0.69
    thansa
    -0.66
     pinggang
    -0.66
    aldehyde
    -0.65
     getchar
    -0.63
     trå
    -0.62
     Marlow
    -0.62
     tfsi
    -0.61
     CommonModule
    -0.61
    MessageInfo
    -0.61
    POSITIVE LOGITS
     predict
    2.02
     prediction
    1.97
     predictions
    1.95
     predicts
    1.87
     Predictions
    1.80
     Prediction
    1.80
     predicting
    1.80
     Predict
    1.77
    predict
    1.76
     predicted
    1.69
    Activations Density 0.224%

    No Known Activations