© 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. 1-CLT-HP
    7. 280
    Prev
    Next
    INDEX
    Explanations

    ab

    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
    TestTools
    -0.60
    Collectors
    -0.58
    baomidou
    -0.49
    igshid
    -0.47
    ########.
    -0.45
    andExpect
    -0.45
     validamos
    -0.44
     hObject
    -0.44
    preduce
    -0.44
     redor
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.63
    Искәрмәләр
    0.59
     تضيفلها
    0.59
    InputTagHelper
    0.59
    ViewFeatures
    0.59
    قایناق‌لار
    0.57
    Населення
    0.56
    ulitis
    0.56
    ">//
    0.56
     BoxDecoration
    0.55
    Activations Density 0.013%

    No Known Activations