© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9306
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     Bourgeois
    -0.61
     bourgeois
    -0.58
     bourgeoisie
    -0.54
    ensk
    -0.52
     eng
    -0.43
    __":
    -0.43
     cach
    -0.42
    lexer
    -0.41
    mdi
    -0.41
     ADV
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.81
    IUrlHelper
    0.78
     mergeFrom
    0.75
    HasAnnotation
    0.73
    IndentedString
    0.71
     Wiktionnaire
    0.69
     parseFrom
    0.68
    rungsseite
    0.66
    SuppressMessage
    0.65
     ویکی‌پدی
    0.65
    Activations Density 0.004%

    No Known Activations