© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8840
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
    Negative Logits
     Cæsar
    -0.65
     ویکی‌پدیا
    -0.63
     allowing
    -0.61
     although
    -0.61
     bringing
    -0.61
     removing
    -0.61
     delivering
    -0.60
     introducing
    -0.59
     inviting
    -0.58
     accepting
    -0.57
    POSITIVE LOGITS
    GOTREF
    0.43
    Aholisi
    0.42
    []
    0.42
     hauteur
    0.42
    Demografia
    0.41
    htbp
    0.41
    lccn
    0.40
    [],
    0.40
    Cyfeiriadau
    0.39
    {%
    0.39
    Activations Density 0.502%

    No Known Activations