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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74792
    Prev
    Next
    INDEX
    Explanations

    '

    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
     vrais
    -0.56
     amitié
    -0.54
     noDo
    -0.54
     république
    -0.50
     étrangères
    -0.49
     setuptools
    -0.48
     cuarzo
    -0.48
     subsequence
    -0.48
     démocratie
    -0.48
    Gön
    -0.47
    POSITIVE LOGITS
    énario
    0.63
    awtextra
    0.59
    Diweddarwch
    0.59
    AsUp
    0.57
     otomatig
    0.56
    +#+#
    0.56
    hoeddwyd
    0.53
     hire
    0.51
     mould
    0.49
     بيها
    0.47
    Activations Density 0.003%

    No Known Activations