© 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. 1506
    Prev
    Next
    INDEX
    Explanations

    -ise/-ize

    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
     neighbors
    -0.61
     favor
    -0.61
     Еще
    -0.60
     tumors
    -0.60
     theater
    -0.59
    Neighbors
    -0.59
     rumors
    -0.59
     harbor
    -0.58
     Ее
    -0.58
     theaters
    -0.58
    POSITIVE LOGITS
    RegressionTest
    0.98
     generalised
    0.97
    脚注の使い方
    0.92
    <bos>
    0.92
     standardised
    0.91
    expandindo
    0.91
     randomised
    0.91
     fertiliser
    0.88
     localised
    0.88
     recognisable
    0.88
    Activations Density 0.149%

    No Known Activations