© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92068
    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
    DllImport
    -0.52
    ttino
    -0.49
    RetentionPolicy
    -0.49
    YECTO
    -0.44
    ανε
    -0.43
     ích
    -0.43
    更高的
    -0.42
     desembar
    -0.42
    ände
    -0.42
     dụ
    -0.41
    POSITIVE LOGITS
     it
    0.77
    antMatchers
    0.75
    mybatisplus
    0.74
    IUrlHelper
    0.71
    tagHelperRunner
    0.70
     @"/
    0.69
    expandindo
    0.68
     AssemblyTitle
    0.66
     Wikimedijinoj
    0.63
     typelib
    0.63
    Activations Density 0.002%

    No Known Activations