© 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. 5-CLT-HP
    7. 190
    Prev
    Next
    INDEX
    Explanations

    fowl

    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
     feathers
    -0.66
    Feather
    -0.64
     Feathers
    -0.61
     Feather
    -0.60
     feather
    -0.59
     birds
    -0.59
    Birds
    -0.59
    feather
    -0.59
     BIRDS
    -0.59
     Birds
    -0.58
    POSITIVE LOGITS
     périodes
    0.61
     universale
    0.60
     marié
    0.59
     domés
    0.59
     économies
    0.59
     supérieures
    0.56
     tár
    0.55
     altrimenti
    0.54
     soltar
    0.54
     tempio
    0.53
    Activations Density 0.000%

    No Known Activations