© 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. 5-CLT-HP
    7. 6222
    Prev
    Next
    INDEX
    Explanations

    financial reporting

    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
     HasFactory
    -0.63
    orical
    -0.54
     during
    -0.52
     durante
    -0.49
     gedurende
    -0.47
    during
    -0.46
    ximadamente
    -0.45
    országban
    -0.45
     طی
    -0.45
     durant
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.67
    LookAnd
    0.63
    出版年
    0.62
     ComVisible
    0.62
    nestjs
    0.61
     pinulongan
    0.55
     EconPapers
    0.55
    TypedDataSet
    0.55
    abetes
    0.54
    AddField
    0.53
    Activations Density 0.008%

    No Known Activations