© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1596
    Prev
    Next
    INDEX
    Explanations

    it

    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
     campana
    -0.49
     galinha
    -0.47
    GeneratedValue
    -0.47
     querem
    -0.44
    point
    -0.44
    sign
    -0.43
    guna
    -0.43
    PreAuthorize
    -0.43
     invitation
    -0.42
     signUp
    -0.42
    POSITIVE LOGITS
    
    0.63
    fromnode
    0.61
    tagHelperRunner
    0.60
     CreateTagHelper
    0.58
     initComponents
    0.57
    apest
    0.56
     '
    0.56
    pushFollow
    0.54
    تقاوى
    0.54
    ++
    0.54
    Activations Density 0.002%

    No Known Activations