© 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. 1-CLT-HP
    7. 14701
    Prev
    Next
    INDEX
    Explanations

    chemical materials

    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
     propOrder
    -0.65
    AddTagHelper
    -0.60
     Voit
    -0.54
    neath
    -0.53
    género
    -0.52
    gling
    -0.52
    yto
    -0.51
    tium
    -0.51
    QMetaType
    -0.51
    nodoc
    -0.48
    POSITIVE LOGITS
     leſs
    0.56
     lefs
    0.52
     <<<<<<<<<<<<<<
    0.52
     juges
    0.48
     stället
    0.47
    hringer
    0.46
     pédagogique
    0.46
     AtomicInteger
    0.46
     Paglinawan
    0.45
     пожалуйста
    0.45
    Activations Density 0.133%

    No Known Activations