© 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. 40265
    Prev
    Next
    INDEX
    Explanations

    scaling/substances/surfaces

    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
     extérieures
    -0.54
     Glad
    -0.49
     berbahaya
    -0.48
     normaux
    -0.48
     dụng
    -0.47
     publiques
    -0.47
     berbentuk
    -0.47
     tört
    -0.47
     Say
    -0.47
    ystemet
    -0.47
    POSITIVE LOGITS
    enumi
    0.85
    ingly
    0.77
    +#+#
    0.73
     kasarigan
    0.71
     >=",
    0.71
    OGND
    0.70
    BufferException
    0.66
     EconPapers
    0.66
    saraba
    0.64
     fieldNum
    0.64
    Activations Density 0.012%

    No Known Activations