© 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. 1-CLT-HP
    4. 13462
    Prev
    Next
    INDEX
    Explanations

    directions and time

    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
     enfans
    -0.58
     paraître
    -0.55
     blessures
    -0.54
     mères
    -0.54
     comportements
    -0.53
     hijas
    -0.52
     pauvres
    -0.52
     blessés
    -0.52
     prêtres
    -0.51
     múl
    -0.50
    POSITIVE LOGITS
    <bos>
    0.75
    Geplaatst
    0.74
     ContentValues
    0.68
     ThemeData
    0.62
    writerow
    0.61
     الرياضيه
    0.61
    __':
    
    0.60
    openConnection
    0.60
     beginnetje
    0.60
     NSCoder
    0.60
    Activations Density 0.604%

    No Known Activations