© 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. 0-CLT-HP
    4. 43845
    Prev
    Next
    INDEX
    Explanations

    realize

    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
     realize
    -1.13
     realise
    -0.85
     realizes
    -0.75
    انجليز
    -0.72
    RUnlock
    -0.71
    parsedMessage
    -0.69
    UnsafeEnabled
    -0.68
    Zeneca
    -0.68
    ReusableCell
    -0.68
    MeasureSpec
    -0.67
    POSITIVE LOGITS
    ########.
    0.84
     how
    0.63
     mixed
    0.51
     that
    0.50
     Mixed
    0.49
     what
    0.48
     utafitiHapana
    0.48
    sikt
    0.47
     tái
    0.47
    howto
    0.47
    Activations Density 0.035%

    No Known Activations