© 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. 0-CLT-HP
    7. 1339
    Prev
    Next
    INDEX
    Explanations

    lodging or religious building

    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
     castle
    -1.35
     Castle
    -1.21
     palace
    -1.15
     Houſe
    -1.13
     Palace
    -1.10
    Castle
    -1.10
     CASTLE
    -1.09
    castle
    -1.09
     Monfieur
    -1.09
     monastery
    -1.07
    POSITIVE LOGITS
    e
    0.76
    a
    0.58
    ed
    0.57
    i
    0.56
    ه
    0.56
    k
    0.54
    et
    0.53
    o
    0.47
    ember
    0.43
    м
    0.43
    Activations Density 0.099%

    No Known Activations