© 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. 0-CLT-HP
    7. 90627
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
     culturelles
    -0.65
     faibles
    -0.62
     extérieurs
    -0.60
     véritables
    -0.57
    @",
    -0.56
     bästa
    -0.55
     décisions
    -0.54
     mauvaises
    -0.54
     tâches
    -0.53
     présentes
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.78
     становника
    0.73
    +:+
    0.73
     تضيفلها
    0.69
     Cassini
    0.68
     onItemClick
    0.65
     <=",
    0.65
     numberWith
    0.65
    SharedDtor
    0.63
    uría
    0.62
    Activations Density 0.091%

    No Known Activations