© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 42149
    Prev
    Next
    INDEX
    Explanations

    foreign languages (mostly European)

    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
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -3.22
     feroit
    -3.13
     auroit
    -3.06
     étoient
    -3.03
     enfans
    -3.00
     varandra
    -2.94
     étoit
    -2.86
     définiti
    -2.80
     démocr
    -2.75
     automatiques
    -2.72
    POSITIVE LOGITS
     in
    1.32
     di
    1.30
     for
    1.23
     de
    1.20
     and
    1.13
     ad
    1.12
     re
    1.11
     con
    1.09
     to
    1.09
     as
    1.06
    Activations Density 0.160%

    No Known Activations