© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97443
    Prev
    Next
    INDEX
    Explanations

    Bulletin

    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
    astify
    -0.65
     Bulletin
    -0.64
     alerts
    -0.61
     relays
    -0.61
     BULLETIN
    -0.61
     bulletins
    -0.61
     alarms
    -0.59
     rallies
    -0.57
     redirects
    -0.57
     bulletin
    -0.56
    POSITIVE LOGITS
     noires
    0.64
     noastre
    0.54
     prépar
    0.53
     esprits
    0.53
    ValueStyle
    0.53
    ագրություններ
    0.53
     Felder
    0.52
     deschis
    0.52
     CreateTagHelper
    0.50
     totul
    0.50
    Activations Density 0.648%

    No Known Activations