© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97143
    Prev
    Next
    INDEX
    Explanations

    nervous

    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
     nationaux
    -0.89
     prisonniers
    -0.83
    SharedDtor
    -0.79
     généraux
    -0.78
     traités
    -0.76
    StructEnd
    -0.75
     personnalisés
    -0.75
     Administrativna
    -0.75
     illustrazione
    -0.75
     spéciaux
    -0.75
    POSITIVE LOGITS
     elegans
    0.49
     adjuster
    0.45
     system
    0.43
    enteric
    0.42
     endos
    0.41
     Edouard
    0.41
     seaborn
    0.39
     worm
    0.39
     empire
    0.39
     console
    0.39
    Activations Density 0.001%

    No Known Activations