© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    oblast

    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
     horses
    -0.64
    dogs
    -0.63
     potatoes
    -0.62
     lilies
    -0.61
    saraba
    -0.61
     bikes
    -0.61
    oredCriteria
    -0.61
     dogs
    -0.60
    VersionUID
    -0.60
     trees
    -0.60
    POSITIVE LOGITS
     embryo
    0.58
     youngster
    0.57
     fetus
    0.51
     teenager
    0.50
     puppy
    0.49
     toddler
    0.49
     nugget
    0.48
     calf
    0.47
     tanto
    0.47
     student
    0.46
    Activations Density 0.006%

    No Known Activations