© 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. 4-CLT-HP
    7. 4427
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     Roskov
    -1.01
    ✨:
    -0.69
    IVEREF
    -0.63
    __*/
    -0.62
    AnchorStyles
    -0.62
    ')")
    -0.62
    ViewFeatures
    -0.61
    ثيق
    -0.61
    Datuak
    -0.60
    :],
    -0.60
    POSITIVE LOGITS
    UIKit
    0.53
    HandlerContext
    0.49
    JUnit
    0.41
    Node
    0.41
    toMatchSnapshot
    0.40
    ærke
    0.40
    irea
    0.40
     Kansas
    0.39
    weise
    0.39
    unlink
    0.39
    Activations Density 0.003%

    No Known Activations