© 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. 16094
    Prev
    Next
    INDEX
    Explanations

    avia

    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
    avia
    -1.45
    lop
    -1.11
    AVIA
    -0.84
    avian
    -0.82
     mại
    -0.59
    LOP
    -0.58
     lop
    -0.54
    avi
    -0.53
     signs
    -0.53
    ρων
    -0.51
    POSITIVE LOGITS
    AsUp
    0.71
     eventdata
    0.65
    RetentionPolicy
    0.64
     HasFactory
    0.63
    MessageTagHelper
    0.60
     calendriers
    0.60
    esgue
    0.60
     AppColors
    0.59
    AndroidJUnit
    0.58
    #+#
    0.57
    Activations Density 0.009%

    No Known Activations