© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    words related to forecasting or making models

    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
    Not in Any Lists

    No Comments

    Negative Logits
    dotenv
    -0.75
     CommonModule
    -0.73
    triangleq
    -0.71
     SafeMath
    -0.70
    itespace
    -0.69
     Aimee
    -0.68
     testCase
    -0.67
    Kaynakça
    -0.65
     ويكيميديا
    -0.65
    meanor
    -0.65
    POSITIVE LOGITS
     predict
    2.66
     prediction
    2.56
     predictions
    2.45
     predicts
    2.36
     predicting
    2.33
     Prediction
    2.25
     predicted
    2.19
     Predictions
    2.19
    predict
    2.14
    prediction
    2.14
    Activations Density 0.456%

    No Known Activations