© 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. 4-CLT-HP
    7. 1112
    Prev
    Next
    INDEX
    Explanations

    natural occurrences

    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
    hoea
    -0.55
    ⓧ
    -0.51
    مصادر
    -0.50
     तक
    -0.47
     wel
    -0.45
    batim
    -0.45
    égi
    -0.44
     biliary
    -0.43
    await
    -0.42
    vacy
    -0.42
    POSITIVE LOGITS
     naturales
    1.01
     naturelles
    0.95
    Natural
    0.94
     naturais
    0.94
     Natural
    0.94
     natural
    0.94
     naturale
    0.93
     természetes
    0.90
    NATURAL
    0.88
    natural
    0.88
    Activations Density 0.007%

    No Known Activations