© 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. 779
    Prev
    Next
    INDEX
    Explanations

    note

    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
    queryInterface
    -0.69
     @"/
    -0.65
    fromnode
    -0.65
    ="@+
    -0.64
    TagMode
    -0.62
    IVEREF
    -0.60
    AddTagHelper
    -0.58
    Personensuche
    -0.56
    NameInMap
    -0.55
    хьтан
    -0.55
    POSITIVE LOGITS
    mtliche
    0.50
     b
    0.50
     endwhile
    0.49
    ijski
    0.49
    COUVER
    0.48
    boutin
    0.48
     enkelte
    0.47
     angesch
    0.46
    Бележки
    0.46
    lichting
    0.46
    Activations Density 0.014%

    No Known Activations