© 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. 0-CLT-HP
    4. 40182
    Prev
    Next
    INDEX
    Explanations

    representation/description

    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
     canes
    -0.66
     AssemblyProduct
    -0.65
    bootstrapcdn
    -0.65
     avoient
    -0.62
     strut
    -0.60
     makeStyles
    -0.60
     Plenum
    -0.60
     kaynağından
    -0.58
     ControllerBase
    -0.58
     pose
    -0.57
    POSITIVE LOGITS
    sy
    0.58
    find
    0.58
    serv
    0.54
    lg
    0.53
     b
    0.50
    my
    0.50
     porcelaine
    0.50
     excellent
    0.50
     an
    0.49
    script
    0.48
    Activations Density 0.129%

    No Known Activations