© 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. 1-CLT-HP
    7. 323
    Prev
    Next
    INDEX
    Explanations

    buildings and apartments

    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
     houses
    -0.54
     Italijani
    -0.52
    StructEnd
    -0.52
    Houses
    -0.51
     homes
    -0.49
     Houses
    -0.49
     Häuser
    -0.48
    uisine
    -0.46
    createServer
    -0.45
    Diwedd
    -0.45
    POSITIVE LOGITS
    protoimpl
    0.62
     gyhoeddwyd
    0.60
    Enllaces
    0.60
     nahilalakip
    0.58
    BeginContext
    0.57
     wachten
    0.56
     csrf
    0.56
    Tracce
    0.55
    csrf
    0.54
     Harassment
    0.54
    Activations Density 0.117%

    No Known Activations