© 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. 92040
    Prev
    Next
    INDEX
    Explanations

    to

    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
     StatelessWidget
    -0.88
     myſelf
    -0.80
    NUMX
    -0.79
     Infórmanos
    -0.78
    virons
    -0.76
    ſelves
    -0.76
     himſelf
    -0.75
     StatefulWidget
    -0.73
     cherchés
    -0.73
    tagez
    -0.73
    POSITIVE LOGITS
     date
    0.65
     par
    0.60
     scratch
    0.56
     S
    0.52
     s
    0.50
     proper
    0.47
     finally
    0.47
     full
    0.46
     snuff
    0.45
     si
    0.44
    Activations Density 0.001%

    No Known Activations