© 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. 39847
    Prev
    Next
    INDEX
    Explanations

    health

    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
    пуль
    -0.42
    niak
    -0.38
    то
    -0.36
    ๆ
    -0.36
    anato
    -0.36
    var
    -0.36
    ltk
    -0.35
    likleri
    -0.35
     bằng
    -0.35
    は
    -0.35
    POSITIVE LOGITS
     Monfieur
    1.04
    StructEnd
    0.99
     Houſe
    0.96
    sizeCache
    0.93
    InjectAttribute
    0.90
     ComVisible
    0.88
     незавершена
    0.88
    GEBURTSDATUM
    0.87
     houſe
    0.86
    rrggbb
    0.85
    Activations Density 0.569%

    No Known Activations