© 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. 92441
    Prev
    Next
    INDEX
    Explanations

    waterfall

    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
     fall
    -0.94
     Fall
    -0.81
    autumn
    -0.81
    Fall
    -0.71
    Autumn
    -0.69
     autumn
    -0.69
    HasAnnotation
    -0.68
     Autumn
    -0.68
    TagMode
    -0.68
     rentrée
    -0.68
    POSITIVE LOGITS
    ers
    0.65
    page
    0.63
     Theſe
    0.61
    ing
    0.59
     Mosca
    0.59
    r
    0.59
    createTextNode
    0.58
    s
    0.57
     causation
    0.55
    pages
    0.55
    Activations Density 0.299%

    No Known Activations