© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2968
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     CreateTagHelper
    -0.93
    ⓧ
    -0.80
    expandindo
    -0.71
     intptr
    -0.68
     resourceCulture
    -0.65
    
    -0.65
     RSSSF
    -0.62
     Савезне
    -0.61
     Efq
    -0.57
    rativa
    -0.56
    POSITIVE LOGITS
    IndentedString
    0.49
     BoxDecoration
    0.47
    windowFixed
    0.47
     Cho
    0.47
    urlpatterns
    0.46
    trans
    0.45
    def
    0.44
    Cho
    0.44
     ProtoMessage
    0.43
    sf
    0.43
    Activations Density 0.002%

    No Known Activations