© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72358
    Prev
    Next
    INDEX
    Explanations

    Technical/design context

    np_max-act-logits · 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
     Craft
    -0.62
    aarrggbb
    -0.58
    Craft
    -0.58
    epam
    -0.55
    
    -0.54
    ciated
    -0.52
     pymysql
    -0.52
    nist
    -0.52
     Nerv
    -0.52
     craft
    -0.51
    POSITIVE LOGITS
    richTextPanel
    0.57
     CreateTagHelper
    0.57
     concern
    0.54
     bear
    0.54
    rrggbb
    0.51
    impin
    0.50
    concern
    0.49
     alight
    0.48
     surla
    0.48
    toplankton
    0.48
    Activations Density 0.000%

    No Known Activations