© 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. 91079
    Prev
    Next
    INDEX
    Explanations

    names/titles/words

    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
     morire
    -0.56
     appelés
    -0.51
     déclar
    -0.50
     contextLoads
    -0.50
     lavable
    -0.50
     extérieures
    -0.49
     étoient
    -0.48
     bianche
    -0.48
     Espec
    -0.47
     automatiques
    -0.47
    POSITIVE LOGITS
     that
    0.84
     often
    0.73
     familiar
    0.68
    TintMode
    0.66
    rungsseite
    0.65
     I
    0.65
     frequently
    0.64
    kyat
    0.60
     much
    0.59
     Reverso
    0.59
    Activations Density 0.001%

    No Known Activations