© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97263
    Prev
    Next
    INDEX
    Explanations

    manufacturing and 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
    FormTagHelper
    -0.84
     barnen
    -0.82
     BoxDecoration
    -0.82
     varandra
    -0.82
    AccessorTable
    -0.79
     Monarchy
    -0.77
     Majefty
    -0.77
     Lordship
    -0.74
     forêt
    -0.74
     skolan
    -0.73
    POSITIVE LOGITS
    iness
    0.68
    show
    0.51
    top
    0.51
    ful
    0.50
    skip
    0.50
    maker
    0.50
    stone
    0.49
    -
    0.48
    man
    0.48
    like
    0.48
    Activations Density 0.062%

    No Known Activations