© 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. 16041
    Prev
    Next
    INDEX
    Explanations

    critical, contents

    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
    جوايز
    -0.64
     móviles
    -0.57
     möjligt
    -0.56
     skydd
    -0.56
     spéciaux
    -0.53
     igång
    -0.53
    trona
    -0.51
     arbete
    -0.50
     möjlighet
    -0.50
    liosis
    -0.49
    POSITIVE LOGITS
    daß
    0.53
    OrNil
    0.52
     <<<<<<<<<<<<<<
    0.52
    EndContext
    0.51
     Jefus
    0.49
     blz
    0.49
    ESTRO
    0.48
     MainAxisSize
    0.48
     finesse
    0.48
     universality
    0.48
    Activations Density 0.210%

    No Known Activations