© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    sudden

    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
     للمعارف
    -0.66
    StoryboardSegue
    -0.64
    aarrggbb
    -0.63
    Koordinaten
    -0.56
    ępo
    -0.54
    Portail
    -0.51
     facilitation
    -0.51
     mainly
    -0.51
     Wikimedijinoj
    -0.50
    بوابة
    -0.50
    POSITIVE LOGITS
     nhau
    0.59
     and
    0.57
     switched
    0.52
     popularity
    0.50
    romptu
    0.50
    nexpected
    0.49
     wunder
    0.49
     discovered
    0.49
     burst
    0.48
     popularidad
    0.48
    Activations Density 0.003%

    No Known Activations