© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42074
    Prev
    Next
    INDEX
    Explanations

    activities

    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
     activities
    -1.41
    Activities
    -1.38
     Activities
    -1.33
    activities
    -1.27
     ACTIVITIES
    -1.14
     activités
    -0.96
     actividades
    -0.88
     atividades
    -0.85
    Activity
    -0.82
     aktiviteter
    -0.80
    POSITIVE LOGITS
     dAtA
    0.59
    าสตร์
    0.59
    zędu
    0.58
    >');
    0.57
    +:+
    0.57
     CreateTagHelper
    0.57
     ब्रेकडाउन
    0.56
    HasForeignKey
    0.54
    TagHelper
    0.52
    :✨
    0.52
    Activations Density 0.012%

    No Known Activations