© 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. 96182
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     NSCoder
    -0.60
    webElementXpaths
    -0.60
     pinulongan
    -0.59
    MethodManager
    -0.58
     onData
    -0.58
    logous
    -0.54
     հղումներ
    -0.53
    wyl
    -0.53
    classnames
    -0.53
     springfox
    -0.52
    POSITIVE LOGITS
     nawr
    0.49
    EndGlobalSection
    0.48
     frequent
    0.47
    invokeLater
    0.46
     endregion
    0.45
     protoimpl
    0.45
    ẽ
    0.44
    <?
    0.44
    bisous
    0.44
     now
    0.43
    Activations Density 0.006%

    No Known Activations