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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 696
    Prev
    Next
    INDEX
    Explanations

    B

    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
    addCriterion
    -0.52
     Мексичка
    -0.51
    Personensuche
    -0.48
     повіт
    -0.44
    Ārējās
    -0.43
    vejec
    -0.41
     Allahabad
    -0.40
     >=",
    -0.40
     GlobalKey
    -0.40
    groom
    -0.40
    POSITIVE LOGITS
    Hentet
    0.79
    ModelAdmin
    0.64
    __':
    0.62
    XtraReports
    0.60
     CreateTagHelper
    0.60
    TagHelper
    0.59
     مشين
    0.58
    ModelSerializer
    0.57
    QSize
    0.57
     models
    0.56
    Activations Density 0.022%

    No Known Activations