Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12453
    Prev
    Next
    INDEX
    Explanations

    properties

    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
     للمعارف
    -0.84
    berdayakan
    -0.77
     property
    -0.77
    ineno
    -0.76
     Property
    -0.74
     Италијани
    -0.74
     समीक्षक
    -0.72
    Portale
    -0.71
     properties
    -0.71
    Property
    -0.69
    POSITIVE LOGITS
     (
    0.41
     man
    0.41
     Gleich
    0.41
     Confusion
    0.41
     Educação
    0.39
     giy
    0.38
     graduation
    0.38
     injured
    0.37
     lieben
    0.37
    abstractmethod
    0.37
    Activations Density 0.087%

    No Known Activations