© 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. 5-CLT-HP
    7. 563
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Lun
    -0.58
     rode
    -0.55
     riders
    -0.54
    AsUp
    -0.54
     bicycles
    -0.53
     Clay
    -0.52
     bikes
    -0.50
     mules
    -0.50
     rides
    -0.49
    openzeppelin
    -0.48
    POSITIVE LOGITS
    хьтан
    0.71
     Италијани
    0.62
    씩
    0.60
    AndEndTag
    0.59
     للمعارف
    0.54
    seamnă
    0.54
    pédie
    0.54
     Chwiliwch
    0.52
     unknownFields
    0.52
     invokingState
    0.51
    Activations Density 0.003%

    No Known Activations