© 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. 0-CLT-HP
    7. 90838
    Prev
    Next
    INDEX
    Explanations

    image

    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
     image
    -2.16
     Image
    -1.77
    image
    -1.74
    Image
    -1.69
     images
    -1.63
     IMAGE
    -1.43
    IMAGE
    -1.36
     Images
    -1.34
     imagen
    -1.30
     imagem
    -1.29
    POSITIVE LOGITS
    Демографія
    1.00
     geologists
    0.85
    enderror
    0.84
     geologist
    0.82
    FieldBuilder
    0.79
     sherds
    0.78
     MonoBehaviour
    0.78
     nahilalakip
    0.78
     zirc
    0.77
    DBNull
    0.76
    Activations Density 0.276%

    No Known Activations