© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3965
    Prev
    Next
    INDEX
    Explanations

    science and technology texts

    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
     kepolisian
    -0.50
     sơn
    -0.50
    buch
    -0.49
    brengen
    -0.48
     </
    -0.48
    pis
    -0.47
     Ter
    -0.46
    beginTransaction
    -0.46
    ksyon
    -0.46
    TabIndex
    -0.46
    POSITIVE LOGITS
    OGND
    0.71
     Roskov
    0.70
     становника
    0.68
    awtextra
    0.62
    quelize
    0.60
    verwijspagina
    0.59
    Населення
    0.54
    ंदीखरीदारी
    0.52
    pédie
    0.52
    udesta
    0.52
    Activations Density 0.000%

    No Known Activations