© 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. 91036
    Prev
    Next
    INDEX
    Explanations

    on click

    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
    Personendaten
    -0.68
     betweenstory
    -0.65
    IsMutable
    -0.65
    rungsseite
    -0.64
    ParallelGroup
    -0.63
     [*]
    -0.60
    +#+#
    -0.58
    حياتها
    -0.55
    الحياه
    -0.55
    GEBURTSDATUM
    -0.55
    POSITIVE LOGITS
     on
    0.58
     industriels
    0.53
     énergé
    0.52
    inflater
    0.52
     croit
    0.52
     faudra
    0.51
     fenêtres
    0.51
     crítico
    0.50
     sauvages
    0.49
     berbasis
    0.48
    Activations Density 0.002%

    No Known Activations