© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91170
    Prev
    Next
    INDEX
    Explanations

    Contains "ung"

    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
    ung
    -1.05
    UNG
    -0.84
    ungs
    -0.76
    GBT
    -0.73
     AssemblyTitle
    -0.68
    AccessorTable
    -0.64
    
    -0.64
     jsPsych
    -0.63
     QI
    -0.63
     ProtoMessage
    -0.62
    POSITIVE LOGITS
     géographique
    0.65
    TemporalType
    0.57
     compounds
    0.50
    andaag
    0.49
    Insee
    0.48
     geografic
    0.48
    Acknowledgement
    0.47
    ніципалі
    0.47
    bootstrapcdn
    0.47
    omiast
    0.47
    Activations Density 0.106%

    No Known Activations