© 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. 46241
    Prev
    Next
    INDEX
    Explanations

    predicting text

    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
     Савезне
    -0.75
     scoperta
    -0.68
     ouvertes
    -0.65
     ouverts
    -0.65
     vägen
    -0.64
    tagHelperRunner
    -0.63
     pinulongan
    -0.59
     חיצוניים
    -0.59
    couvrir
    -0.57
     виправивши
    -0.56
    POSITIVE LOGITS
     Ponds
    0.60
     Rivers
    0.54
     Lakes
    0.49
     Pond
    0.49
     Volcano
    0.47
     hands
    0.47
     Mountain
    0.47
    Pond
    0.46
     Rocks
    0.46
     Waves
    0.46
    Activations Density 0.005%

    No Known Activations