© 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. 4-CLT-HP
    7. 2779
    Prev
    Next
    INDEX
    Explanations

    Paula

    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
    AddTagHelper
    -0.87
     Paola
    -0.78
     purpoſe
    -0.61
     Monfieur
    -0.59
    Paola
    -0.58
     ſta
    -0.57
     chré
    -0.57
     auffi
    -0.57
    "",
    -0.57
     Telex
    -0.56
    POSITIVE LOGITS
    oneofs
    0.54
    findById
    0.49
     sekali
    0.47
    htar
    0.44
    ATIV
    0.43
    SwingConstants
    0.43
    nique
    0.43
    {~
    0.42
    inel
    0.42
    unsqueeze
    0.41
    Activations Density 0.036%

    No Known Activations