© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    HTML tables

    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
     kasarigan
    -0.59
     colorés
    -0.54
    uxxxx
    -0.54
    Driven
    -0.53
     follow
    -0.50
    diğinde
    -0.49
    ADT
    -0.49
    uoco
    -0.48
     journaux
    -0.48
    ┓
    -0.47
    POSITIVE LOGITS
    Spoljašnje
    0.58
    StoryboardSegue
    0.57
     发表于
    0.54
     of
    0.54
     BeautifulSoup
    0.53
    oneofs
    0.51
    ViewFeatures
    0.50
    styleType
    0.50
     unary
    0.48
    engarkan
    0.48
    Activations Density 0.024%

    No Known Activations