© 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. 5-CLT-HP
    7. 91666
    Prev
    Next
    INDEX
    Explanations

    book

    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
    agn
    -0.46
    ฏิ
    -0.43
    景
    -0.43
    StoreMessageInfo
    -0.42
     ${({
    -0.42
    stateProvider
    -0.42
    equipe
    -0.41
     Cib
    -0.40
    Artículo
    -0.40
    issau
    -0.40
    POSITIVE LOGITS
     propOrder
    0.84
     pages
    0.84
     otomatig
    0.73
    AsUp
    0.73
     publisher
    0.72
     publishers
    0.70
     saites
    0.69
     publishing
    0.68
     books
    0.68
    helves
    0.68
    Activations Density 0.003%

    No Known Activations