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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46017
    Prev
    Next
    INDEX
    Explanations

    prediction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prediction
    -1.11
     predict
    -1.07
     predicting
    -1.06
     predicted
    -1.04
     Prediction
    -1.02
    Prediction
    -1.02
    prediction
    -0.98
     predictions
    -0.92
     Predictions
    -0.91
    Predict
    -0.90
    POSITIVE LOGITS
    UrlResolution
    0.73
     volon
    0.58
    ########.
    0.54
     fédéral
    0.54
    CPtr
    0.52
    urra
    0.51
    茅
    0.50
    OREM
    0.50
     XY
    0.50
    nbsp
    0.50
    Activations Density 0.017%

    No Known Activations