© 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. 1-CLT-HP
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    source

    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
     morire
    -0.61
    TagMode
    -0.59
     varandra
    -0.59
     figliu
    -0.57
     berätt
    -0.57
    ArgsConstructor
    -0.57
    AutoresizingMask
    -0.57
     nemici
    -0.57
    urations
    -0.56
    BoxLayout
    -0.56
    POSITIVE LOGITS
    LookAnd
    0.59
     of
    0.56
     copy
    0.52
     address
    0.48
    Abitanti
    0.47
     autorytatywna
    0.47
     doc
    0.44
     препратки
    0.43
     transférez
    0.42
    jspb
    0.42
    Activations Density 0.013%

    No Known Activations