© 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. 1-CLT-HP
    4. 46038
    Prev
    Next
    INDEX
    Explanations

    resistance in 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
     '\\;'
    -0.91
     resistance
    -0.84
    ReusableCell
    -0.83
    abetes
    -0.81
    Resistance
    -0.81
     resisting
    -0.79
     Resistance
    -0.79
    resistance
    -0.78
     resistant
    -0.78
    Personensuche
    -0.77
    POSITIVE LOGITS
     to
    0.65
    to
    0.41
    фици
    0.40
    denes
    0.40
    ty
    0.40
    chern
    0.40
    ydı
    0.39
    wohnt
    0.38
     in
    0.38
    invokeLater
    0.38
    Activations Density 0.038%

    No Known Activations