© 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. 94547
    Prev
    Next
    INDEX
    Explanations

    2

    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
    yntaxException
    -0.54
    曖昧さ回避
    -0.50
    Dobrý
    -0.50
     potete
    -0.50
    WEBPACK
    -0.49
    principalColumn
    -0.49
    BorderLayout
    -0.48
    unchecked
    -0.48
     تكبرها
    -0.47
     SVC
    -0.47
    POSITIVE LOGITS
     Diabetes
    0.68
    styleUrls
    0.63
     Affiliations
    0.59
    LabelTagHelper
    0.57
    Denomin
    0.56
    Manbalar
    0.52
     Dise
    0.52
     Diz
    0.52
     Disease
    0.51
    setVerticalGroup
    0.51
    Activations Density 0.001%

    No Known Activations