© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1523
    Prev
    Next
    INDEX
    Explanations

    locations/organizations

    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
     located
    -0.77
     situés
    -0.76
     fermés
    -0.69
     tendenza
    -0.63
     CreateTagHelper
    -0.62
     localizado
    -0.60
     domicilio
    -0.59
     extérieurs
    -0.59
    ⎩
    -0.58
     Located
    -0.57
    POSITIVE LOGITS
     Penh
    0.62
    Lus
    0.59
     Concordia
    0.58
    contentLoaded
    0.57
     Enlight
    0.55
    andaag
    0.54
    es
    0.53
     Charlemagne
    0.53
    ing
    0.53
     Lus
    0.52
    Activations Density 0.330%

    No Known Activations