© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94747
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     ModelExpression
    -0.87
    TagMode
    -0.76
    OGND
    -0.75
    setVerticalGroup
    -0.75
    AutoresizingMask
    -0.72
     CreateTagHelper
    -0.72
    UnsafeEnabled
    -0.71
     BorderRadius
    -0.68
    WriteTagHelper
    -0.68
    IntoConstraints
    -0.67
    POSITIVE LOGITS
     Winaray
    0.52
    look
    0.52
     ?>>
    0.47
    cetto
    0.45
    %)$
    0.45
    みてください
    0.44
     πό
    0.44
    ?
    0.44
     who
    0.43
    who
    0.43
    Activations Density 0.004%

    No Known Activations