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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2445
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     isComment
    -0.73
     BrowserModule
    -0.59
     Bayard
    -0.57
    IMPORTED
    -0.56
     Instrument
    -0.52
    ListItemIcon
    -0.51
     pleaſure
    -0.50
    TestBase
    -0.50
     kurtka
    -0.48
     koszulka
    -0.48
    POSITIVE LOGITS
     Rust
    0.63
    Rust
    0.54
    ouble
    0.54
    protoimpl
    0.52
     dott
    0.49
    ән
    0.47
    UST
    0.47
    imedes
    0.47
    __(/*!
    0.47
    ustering
    0.46
    Activations Density 0.006%

    No Known Activations