© 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. 1-CLT-HP
    4. 13260
    Prev
    Next
    INDEX
    Explanations

    more

    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
     nahilalakip
    -0.81
    BeginInit
    -0.75
    ValueStyle
    -0.68
     समीक्षाएं
    -0.60
    GIVEREF
    -0.59
     kasarigan
    -0.57
     المعيارى
    -0.57
    RemoveField
    -0.57
    AddTagHelper
    -0.56
    IContainer
    -0.56
    POSITIVE LOGITS
     of
    0.58
    führt
    0.51
    SuppressWarnings
    0.49
     Georgina
    0.48
     chung
    0.47
    WEBPACK
    0.47
     ActionResult
    0.47
    ANSA
    0.47
     IActionResult
    0.47
    mans
    0.47
    Activations Density 0.077%

    No Known Activations