© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76962
    Prev
    Next
    INDEX
    Explanations

    French words

    np_max-act-logits · 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
     Indias
    -1.30
     childs
    -1.15
     womens
    -1.08
     Gods
    -1.02
     Smiths
    -1.02
    Heres
    -1.01
     mans
    -1.01
    Whats
    -1.00
     Toms
    -0.99
     Womens
    -0.98
    POSITIVE LOGITS
     découvertes
    0.56
     vœux
    0.54
     démocr
    0.54
     supérieures
    0.53
     autorités
    0.53
     varandra
    0.51
     religieuses
    0.51
     lèvres
    0.51
     supérieurs
    0.51
     récentes
    0.51
    Activations Density 0.008%

    No Known Activations