© 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. 1-CLT-HP
    7. 46165
    Prev
    Next
    INDEX
    Explanations

    use

    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
     use
    -0.64
    use
    -0.56
    ov
    -0.53
     externi
    -0.52
    ing
    -0.49
     long
    -0.49
    full
    -0.49
    ps
    -0.49
    RSpec
    -0.48
    ine
    -0.48
    POSITIVE LOGITS
    WriteTagHelper
    0.59
     photolibrary
    0.58
     ListNode
    0.56
     addItem
    0.55
     lakhs
    0.55
     Volumes
    0.55
     Coton
    0.54
     LNB
    0.54
     Commencement
    0.54
     tabby
    0.54
    Activations Density 0.035%

    No Known Activations