© 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. 97583
    Prev
    Next
    INDEX
    Explanations

    Munich or Vienna

    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
     Stuttgart
    -0.81
    ')")
    -0.77
     Chicago
    -0.77
     Düsseldorf
    -0.76
     Tokyo
    -0.74
    ()};
    -0.73
     Munich
    -0.71
     Vienna
    -0.69
     CHICAGO
    -0.67
     "));
    -0.65
    POSITIVE LOGITS
    PyExc
    0.67
     Protestantism
    0.64
    parsedMessage
    0.59
     Stray
    0.58
     Affiliations
    0.57
     Huguen
    0.56
     WIC
    0.56
     Morality
    0.55
     ['./
    0.52
     erect
    0.52
    Activations Density 0.115%

    No Known Activations