© 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. 5-CLT-HP
    7. 58
    Prev
    Next
    INDEX
    Explanations

    business, technology

    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
     الحره
    -0.80
     AssemblyTitle
    -0.59
    awtextra
    -0.58
     Kisses
    -0.57
    titleMargin
    -0.56
    رشف
    -0.56
    IsContent
    -0.56
     FontFamily
    -0.56
     viewDidLoad
    -0.54
    AutoScale
    -0.54
    POSITIVE LOGITS
     what
    0.59
    THING
    0.56
     THING
    0.53
     Thing
    0.52
     thing
    0.52
    thing
    0.51
    dymyr
    0.50
    omen
    0.50
    ingue
    0.50
     What
    0.49
    Activations Density 0.000%

    No Known Activations