© 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. 5-CLT-HP
    7. 95162
    Prev
    Next
    INDEX
    Explanations

    much

    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
     tartalomajánló
    -0.70
    AddTagHelper
    -0.66
     EconPapers
    -0.60
    قایناق‌لار
    -0.55
    Datuak
    -0.54
    gráfica
    -0.54
    ArgsConstructor
    -0.54
     Lightboxes
    -0.53
    DeleteBehavior
    -0.53
    MIDDLEWARE
    -0.52
    POSITIVE LOGITS
     with
    0.73
     sozinho
    0.61
     exporting
    0.58
     comigo
    0.57
     conversing
    0.56
     talking
    0.54
    IElement
    0.53
     traveling
    0.52
     travelling
    0.52
     listening
    0.50
    Activations Density 0.002%

    No Known Activations