© 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. 45154
    Prev
    Next
    INDEX
    Explanations

    game or disease

    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
     pouvoirs
    -0.68
     يتيمه
    -0.63
     StatelessWidget
    -0.61
    resiasi
    -0.61
     vœux
    -0.61
    iddler
    -0.60
     tâche
    -0.59
     carreaux
    -0.58
    maketitle
    -0.57
    RectangleBorder
    -0.56
    POSITIVE LOGITS
    archiviato
    0.51
     "..\..\..\
    0.48
     FishBase
    0.47
    GeneratedCode
    0.46
    存于互联网档案馆
    0.46
    kwür
    0.46
     timing
    0.45
    (;;)
    0.44
     constancy
    0.43
    onViewCreated
    0.43
    Activations Density 0.012%

    No Known Activations