© 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. 90670
    Prev
    Next
    INDEX
    Explanations

    accessibility options

    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
    InputBorder
    -0.64
     inspiration
    -0.59
     onAnimation
    -0.59
     inspirations
    -0.57
     Wiktionnaire
    -0.57
    ICIÓN
    -0.57
    emic
    -0.56
    例文
    -0.56
    e
    -0.56
    MessageOf
    -0.54
    POSITIVE LOGITS
    yanka
    0.45
     defaultstate
    0.45
     récentes
    0.44
     fisuras
    0.43
     rayures
    0.43
     compito
    0.42
    ambique
    0.41
    ⓧ
    0.41
    ास्त
    0.40
    CJK
    0.40
    Activations Density 0.272%

    No Known Activations