© 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. 0-CLT-HP
    7. 43467
    Prev
    Next
    INDEX
    Explanations

    cla

    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
     igreja
    -0.47
     férias
    -0.46
     autobuses
    -0.46
     viagens
    -0.43
     service
    -0.43
    SerializedSize
    -0.43
     Wikimédia
    -0.42
     getopt
    -0.42
     business
    -0.41
     tider
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.69
    hysema
    0.67
    EndContext
    0.66
    adaptiveStyles
    0.65
    transQ
    0.65
     ddelweddau
    0.65
     nahilalakip
    0.64
    fficking
    0.64
    vocato
    0.64
     autorytatywna
    0.63
    Activations Density 0.804%

    No Known Activations