© 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. 90841
    Prev
    Next
    INDEX
    Explanations

    image

    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
     EconPapers
    -0.69
     difficiles
    -0.66
    BeginContext
    -0.65
     supérieurs
    -0.65
     sauvages
    -0.63
    väg
    -0.62
    :✨
    -0.61
     définiti
    -0.60
     mineures
    -0.60
     alguno
    -0.60
    POSITIVE LOGITS
    PerformLayout
    0.57
    RegressionTest
    0.52
    EndInit
    0.51
     ujednoznacz
    0.44
    </thead>
    0.43
    rime
    0.42
     gr
    0.42
     gynhyrchwyd
    0.42
    gård
    0.41
    NSNotification
    0.41
    Activations Density 0.010%

    No Known Activations