© 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. 96298
    Prev
    Next
    INDEX
    Explanations

    landscape

    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
     henkil
    -0.64
    ciales
    -0.59
    otto
    -0.58
    izr
    -0.54
    centaje
    -0.52
     käyt
    -0.51
    brigens
    -0.51
     TextAlign
    -0.51
    MessageTagHelper
    -0.51
     todella
    -0.50
    POSITIVE LOGITS
     painting
    0.69
     architecture
    0.68
     paintings
    0.67
     design
    0.62
     aesthetics
    0.61
     painter
    0.58
    SceneManagement
    0.58
     integration
    0.57
     artistry
    0.56
     EconPapers
    0.56
    Activations Density 0.001%

    No Known Activations