© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97621
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
    WindowConstants
    -0.65
    entance
    -0.61
    LookAnd
    -0.59
    onese
    -0.58
     Miscellaneous
    -0.57
    hibian
    -0.54
     jeb
    -0.53
     vendre
    -0.52
     albicans
    -0.52
    gments
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.65
    IntoConstraints
    0.59
    tanleria
    0.57
     насељу
    0.57
     aDecoder
    0.54
     المعيارى
    0.54
    TagMode
    0.54
    الحياه
    0.52
     للمعارف
    0.52
    ModelAdmin
    0.49
    Activations Density 0.093%

    No Known Activations