© 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. 8618
    Prev
    Next
    INDEX
    Explanations

    ror

    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
    olu
    -0.77
    nog
    -0.52
    hok
    -0.50
    n
    -0.48
    buty
    -0.46
    coe
    -0.46
    olution
    -0.45
    con
    -0.45
    ham
    -0.45
     already
    -0.44
    POSITIVE LOGITS
     ویکی‌پدیا
    0.73
    Personendaten
    0.73
    kloped
    0.71
     CreateTagHelper
    0.69
     nonatomic
    0.69
    ſelves
    0.64
    脚注の使い方
    0.63
    ^(@)
    0.62
    findpost
    0.62
    AccessorTable
    0.61
    Activations Density 0.012%

    No Known Activations