© 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. 5-CLT-HP
    7. 92503
    Prev
    Next
    INDEX
    Explanations

    adulthood and maturity

    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
    帖最后由
    -0.63
     насељу
    -0.60
     préférable
    -0.60
     coscienza
    -0.60
     diterima
    -0.59
    Искәрмәләр
    -0.59
     fallu
    -0.59
     gostaria
    -0.59
     protoimpl
    -0.58
     voix
    -0.56
    POSITIVE LOGITS
    tagHelper
    0.56
    webElement
    0.51
     flood
    0.49
    classnames
    0.47
     baker
    0.47
    RenderAtEndOf
    0.47
     AssemblyCulture
    0.47
     te
    0.45
     cluster
    0.43
     band
    0.42
    Activations Density 0.000%

    No Known Activations