© 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. 5-CLT-HP
    7. 2704
    Prev
    Next
    INDEX
    Explanations

    pation

    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
     [
    -0.43
     analysis
    -0.41
    อล
    -0.40
     pair
    -0.40
    ene
    -0.40
     
    -0.40
     tant
    -0.38
     study
    -0.38
    zé
    -0.37
    gh
    -0.36
    POSITIVE LOGITS
    featureID
    1.09
     تضيفلها
    1.05
    DeleteBehavior
    0.99
    Portail
    0.98
    ftagPool
    0.98
    CloseOperation
    0.95
     propOrder
    0.93
    SharedCtor
    0.93
    sizeCache
    0.93
    #+#
    0.93
    Activations Density 0.001%

    No Known Activations