© 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. 92326
    Prev
    Next
    INDEX
    Explanations

    reviews/assessments

    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
    ConstraintMaker
    -0.50
     Corazón
    -0.47
    uda
    -0.46
     vasta
    -0.43
    centralwidget
    -0.42
     <<
    -0.41
    jewództ
    -0.40
     parla
    -0.40
     Hyg
    -0.39
    For
    -0.39
    POSITIVE LOGITS
    endphp
    0.62
    
    0.62
    ptonshire
    0.61
    MethodManager
    0.60
    rawDesc
    0.60
     autorytatywna
    0.60
     enfans
    0.59
     acceptez
    0.59
     métiers
    0.57
     Efq
    0.57
    Activations Density 0.002%

    No Known Activations