© 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. 45468
    Prev
    Next
    INDEX
    Explanations

    change, processes

    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
     develop
    -2.38
     develops
    -2.03
    develop
    -1.84
     Develop
    -1.77
    Develop
    -1.54
     DEVELOP
    -1.32
     developed
    -1.23
     desarrollar
    -1.23
    developing
    -1.21
    DEVELOP
    -1.20
    POSITIVE LOGITS
     Diſ
    0.73
     Majefty
    0.60
     ſmall
    0.60
     ſtre
    0.59
     greateſt
    0.56
     a
    0.55
     Reſ
    0.55
     ſeveral
    0.55
     diſt
    0.53
     Anſ
    0.53
    Activations Density 0.089%

    No Known Activations