© 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. 1-CLT-HP
    7. 9256
    Prev
    Next
    INDEX
    Explanations

    their

    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
     showing
    -0.83
     show
    -0.82
     shows
    -0.78
     showed
    -0.77
     Showing
    -0.71
     menunjukkan
    -0.70
    show
    -0.69
     shown
    -0.68
     montrer
    -0.66
    Shows
    -0.66
    POSITIVE LOGITS
    featureID
    0.94
    EDEFAULT
    0.90
     @"/
    0.83
    ########.
    0.78
     فريبيس
    0.77
    évaluateur
    0.77
    SharedDtor
    0.75
    исленность
    0.70
     Normdatei
    0.69
    تقاوى
    0.68
    Activations Density 0.067%

    No Known Activations