© 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. 5-CLT-HP
    7. 4009
    Prev
    Next
    INDEX
    Explanations

    math and numbers

    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
    ums
    -0.48
    keys
    -0.45
     تضيفلها
    -0.45
    setContentView
    -0.44
     rein
    -0.44
     direct
    -0.43
    ses
    -0.43
    Superview
    -0.43
    es
    -0.41
    nesses
    -0.41
    POSITIVE LOGITS
     ویکی‌پدی
    0.79
     estekak
    0.66
     beginnetje
    0.66
     vectorielles
    0.65
    RenderAtEndOf
    0.64
     lèvres
    0.62
     témoins
    0.61
    تقاوى
    0.61
    Климат
    0.60
    Билгалдахарш
    0.60
    Activations Density 0.008%

    No Known Activations