© 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. 77778
    Prev
    Next
    INDEX
    Explanations

    software systems

    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
     تضيفلها
    -0.66
    EndProject
    -0.57
    featureID
    -0.56
    ValueStyle
    -0.56
     autorytatywna
    -0.55
    IVEREF
    -0.54
    tagHelperRunner
    -0.53
    bootstrapcdn
    -0.50
    }{*}{
    -0.49
     Infórmanos
    -0.49
    POSITIVE LOGITS
     system
    0.66
     application
    0.62
     connection
    0.57
     debugging
    0.54
     configuration
    0.53
     runtime
    0.53
     low
    0.51
     Tracing
    0.51
     platform
    0.50
     systeem
    0.50
    Activations Density 0.000%

    No Known Activations