© 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. 1-CLT-HP
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    licenses and copyright notices

    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
     culturelles
    -0.79
     juridiques
    -0.78
     découvertes
    -0.72
     présidenti
    -0.70
     colorés
    -0.64
     judiciales
    -0.62
     liberación
    -0.61
     religieuses
    -0.60
     télécharge
    -0.59
     mauvaises
    -0.59
    POSITIVE LOGITS
    +#+
    0.57
     désolés
    0.56
     препратки
    0.50
     Rá
    0.49
    >.</
    0.49
     }}"></
    0.48
    awtextra
    0.48
     fieldNum
    0.48
     talk
    0.47
     DON
    0.47
    Activations Density 0.005%

    No Known Activations