© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 108
    Prev
    Next
    INDEX
    Explanations

    take

    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
    Personendaten
    -0.66
    DoubleQuotes
    -0.61
     conmigo
    -0.60
     "..\..\..\
    -0.59
    ThroughAttribute
    -0.59
     "..\..\
    -0.57
     nemlig
    -0.56
     préférence
    -0.56
     ABOUT
    -0.55
     voulons
    -0.55
    POSITIVE LOGITS
     you
    0.62
    帖最后由
    0.59
     upto
    0.58
     trial
    0.58
     تضيفلها
    0.57
    trial
    0.55
     some
    0.54
     weeks
    0.50
     retries
    0.49
     up
    0.49
    Activations Density 0.003%

    No Known Activations