© 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. 92653
    Prev
    Next
    INDEX
    Explanations

    cz

    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
     exceeded
    -0.62
     تضيفلها
    -0.62
    cz
    -0.60
    
    -0.60
     surpassed
    -0.59
    Rhestr
    -0.59
    AnchorTagHelper
    -0.58
    ppelin
    -0.56
    TestingModule
    -0.55
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
     "..\..\
    0.59
     صوتيه
    0.59
     gynhyrchwyd
    0.59
     للاسماء
    0.58
     "..\..\..\
    0.57
     correspondance
    0.57
     Liberation
    0.56
     ám
    0.55
     Partai
    0.54
     magique
    0.52
    Activations Density 0.953%

    No Known Activations