© 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. 462
    Prev
    Next
    INDEX
    Explanations

    to by

    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
     '>=
    -0.50
    epik
    -0.47
    unque
    -0.47
    localtime
    -0.43
    ecap
    -0.41
     SearchView
    -0.40
    uição
    -0.39
    vagrant
    -0.38
     Collapse
    -0.36
    acité
    -0.36
    POSITIVE LOGITS
     GenerationType
    0.68
     kaarangay
    0.68
    Portail
    0.68
    jsonwebtoken
    0.64
     AssemblyTitle
    0.63
    olfen
    0.63
    Hentet
    0.62
    expandindo
    0.62
    nolia
    0.61
    contentLoaded
    0.61
    Activations Density 0.002%

    No Known Activations