© 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. 20-CLT-HP
    7. 75284
    Prev
    Next
    INDEX
    Explanations

    make

    np_max-act-logits · 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
    Personendaten
    -0.94
    SourceChecksum
    -0.73
    IUrlHelper
    -0.72
     chaleur
    -0.70
     متعلقه
    -0.66
     bonté
    -0.66
    Зноскі
    -0.65
     colère
    -0.65
     dignité
    -0.65
    انيف
    -0.64
    POSITIVE LOGITS
     sense
    0.68
     s
    0.60
     since
    0.55
     commercial
    0.54
     economic
    0.54
     biological
    0.53
     metallurgical
    0.51
     taxonomic
    0.50
     heads
    0.49
     epidemiological
    0.49
    Activations Density 0.002%

    No Known Activations