© 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. 5-CLT-HP
    7. 5436
    Prev
    Next
    INDEX
    Explanations

    Subject

    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
    клопе
    -0.73
     pinulongan
    -0.65
     Walkover
    -0.62
    WireFormat
    -0.57
    +#+#
    -0.57
     call
    -0.56
     kasarigan
    -0.53
    rise
    -0.52
    marvin
    -0.52
    ArrowToggle
    -0.51
    POSITIVE LOGITS
    extAlignment
    0.61
     doInBackground
    0.59
    EnableWeb
    0.54
    Amicalement
    0.54
     WebApplication
    0.52
     AppColors
    0.52
     imageNamed
    0.47
     TableColumn
    0.46
    ніципалі
    0.46
    gelopen
    0.44
    Activations Density 0.020%

    No Known Activations