© 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. 20-CLT-HP
    7. 74787
    Prev
    Next
    INDEX
    Explanations

    city

    np_max-act-logits · 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
    GenerationType
    -0.74
    abestanden
    -0.59
    ViewFeatures
    -0.52
    onViewCreated
    -0.50
    ########.
    -0.46
    prefixer
    -0.46
     PyLong
    -0.46
     onCreateView
    -0.44
     QtCore
    -0.44
    НИК
    -0.43
    POSITIVE LOGITS
     réve
    0.69
     souris
    0.67
    PASS
    0.60
    NOPQRST
    0.60
     Winery
    0.54
    таратура
    0.54
    ThemeProvider
    0.53
     Directory
    0.52
     Mice
    0.52
     mice
    0.52
    Activations Density 0.001%

    No Known Activations