© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2752
    Prev
    Next
    INDEX
    Explanations

    Quality

    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
     medesimo
    -0.73
     démocratie
    -0.71
     aceea
    -0.70
     poussière
    -0.66
     tâche
    -0.66
     réglementation
    -0.65
     popoli
    -0.65
     bonté
    -0.63
     provisoire
    -0.62
     vantaggio
    -0.61
    POSITIVE LOGITS
     movement
    0.50
     relationship
    0.48
     Amalgam
    0.47
    रिक
    0.47
    )}
    0.47
     Corte
    0.46
    amal
    0.45
     meal
    0.44
     marital
    0.44
     producti
    0.44
    Activations Density 0.002%

    No Known Activations