© 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. 4-CLT-HP
    7. 4990
    Prev
    Next
    INDEX
    Explanations

    colons and parentheses

    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
     تانيه
    -0.71
    IsContent
    -0.71
     فريبيس
    -0.70
     سكانية
    -0.69
    Filmographie
    -0.66
     ainfi
    -0.61
     felizes
    -0.60
    Portale
    -0.60
    rungsseite
    -0.59
     marinho
    -0.59
    POSITIVE LOGITS
     ik
    0.59
     Focus
    0.57
     looking
    0.57
     to
    0.56
     Looking
    0.55
     Mark
    0.54
     Mr
    0.54
    ame
    0.53
    res
    0.53
     so
    0.53
    Activations Density 0.004%

    No Known Activations