© 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. 4-CLT-HP
    7. 2237
    Prev
    Next
    INDEX
    Explanations

    Error

    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
    WebVitals
    -0.80
    setVerticalGroup
    -0.77
    ConstraintMaker
    -0.75
    AnimationsModule
    -0.74
    rungsseite
    -0.74
    Bibliograf
    -0.73
     initComponents
    -0.72
    bootstrapcdn
    -0.72
     للاسماء
    -0.72
    HtmlAttribute
    -0.71
    POSITIVE LOGITS
    .
    0.69
    .,
    0.54
    us
    0.53
    .)
    0.50
    ."
    0.47
     
    0.47
    .).
    0.47
    .</
    0.47
    form
    0.46
     odd
    0.46
    Activations Density 0.000%

    No Known Activations