© 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. 0-CLT-HP
    7. 95704
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
    aden
    -1.34
    truded
    -0.79
    에
    -0.63
     में
    -0.55
     میں
    -0.53
     vectorielles
    -0.52
    みに
    -0.51
     Entra
    -0.50
     carrés
    -0.49
    ánto
    -0.49
    POSITIVE LOGITS
    enumi
    0.63
    '],$
    0.63
    MergeFrom
    0.60
     المعيارى
    0.60
    PerformLayout
    0.57
    eschön
    0.57
    CONCURRENT
    0.56
    ubri
    0.55
     conmigo
    0.54
    Przypisy
    0.53
    Activations Density 0.490%

    No Known Activations