© 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. 1-CLT-HP
    7. 13263
    Prev
    Next
    INDEX
    Explanations

    super

    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
     super
    -0.96
    super
    -0.82
     Super
    -0.81
    SUPER
    -0.80
     SUPER
    -0.77
    Super
    -0.75
     súper
    -0.70
     superpower
    -0.68
    超
    -0.65
    Супер
    -0.63
    POSITIVE LOGITS
     lenker
    0.77
     cherchés
    0.71
    featureID
    0.71
    expandindo
    0.69
    Manbalar
    0.65
    TagMode
    0.63
    Atsauces
    0.60
     esternos
    0.59
    MIDDLEWARE
    0.59
    bootstrapcdn
    0.56
    Activations Density 0.087%

    No Known Activations