© 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. 4-CLT-HP
    7. 918
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Caritas
    -0.52
    úl
    -0.45
    Classes
    -0.45
     appreciate
    -0.41
    gucigalpa
    -0.41
    ModelAttribute
    -0.40
    CLASSES
    -0.40
     last
    -0.40
    <![
    -0.39
    醛
    -0.39
    POSITIVE LOGITS
    حياتها
    0.73
     protoimpl
    0.66
    ⓧ
    0.65
    GOTREF
    0.62
    Архівовано
    0.61
    Personensuche
    0.60
    Cordialement
    0.59
    tldr
    0.59
    Datuak
    0.57
     Normdatei
    0.57
    Activations Density 0.004%

    No Known Activations