© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91209
    Prev
    Next
    INDEX
    Explanations

    hyphens/apostrophes

    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
    <bos>
    -2.31
    webElementXpaths
    -0.97
    MigrationBuilder
    -0.87
    sizeCache
    -0.85
     Савезне
    -0.81
     '\\;'
    -0.78
     nahilalakip
    -0.78
    IndentedString
    -0.77
    WithIOException
    -0.77
     disambiguazione
    -0.74
    POSITIVE LOGITS
    kob
    0.50
    ILEY
    0.47
    IMON
    0.47
    standard
    0.45
    año
    0.45
    Ix
    0.44
     colspan
    0.44
     JAXBElement
    0.44
     nis
    0.43
    umbi
    0.43
    Activations Density 0.028%

    No Known Activations