© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    Equilateral/Code

    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
     Réponses
    -0.77
    contentLoaded
    -0.74
    BeforeAll
    -0.62
    MLLoader
    -0.62
    consulté
    -0.61
    tagHelperRunner
    -0.60
    fitrión
    -0.60
     bonté
    -0.60
    Datuak
    -0.59
     charité
    -0.59
    POSITIVE LOGITS
     malin
    0.43
     Benin
    0.43
     fak
    0.42
     calm
    0.42
     Spitz
    0.42
    pang
    0.40
    Magenta
    0.40
    Fran
    0.40
     cic
    0.39
    prä
    0.39
    Activations Density 0.001%

    No Known Activations