© 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. 8804
    Prev
    Next
    INDEX
    Explanations

    offer

    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
     up
    -0.70
    ########.
    -0.50
     StatelessWidget
    -0.49
    RTCK
    -0.47
     *)__
    -0.46
    Preparazione
    -0.44
    up
    -0.44
    DataPropertyName
    -0.44
    TokenNameLBRACE
    -0.43
    #
    -0.43
    POSITIVE LOGITS
     itſelf
    0.68
     Babyl
    0.67
    saurus
    0.66
    asyarakat
    0.65
     pleaſure
    0.64
     astronomers
    0.63
     Europeans
    0.63
     archaeologists
    0.63
     Theſe
    0.63
     Athenians
    0.62
    Activations Density 0.007%

    No Known Activations