© 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. 635
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     email
    -0.53
    email
    -0.47
    Email
    -0.40
    Ur
    -0.39
    makeText
    -0.38
    e
    -0.37
     Harrington
    -0.37
     este
    -0.37
     emailed
    -0.36
     dieses
    -0.35
    POSITIVE LOGITS
    contentLoaded
    0.89
    IonicModule
    0.86
     autorytatywna
    0.83
    DrawerToggle
    0.83
     виправивши
    0.82
    ModelAdmin
    0.82
    
    0.82
     AssemblyCulture
    0.81
    LookAnd
    0.80
    MessageTagHelper
    0.79
    Activations Density 0.002%

    No Known Activations