© 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. 97998
    Prev
    Next
    INDEX
    Explanations

    code/technical snippets

    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
    AutoScaleMode
    -0.61
     EClass
    -0.54
    SharedCtor
    -0.52
    gridy
    -0.49
     Paglinawan
    -0.48
    Sqft
    -0.48
    ureusement
    -0.47
    ohyd
    -0.47
     Тя
    -0.47
    ίναι
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.83
     الحره
    0.71
    Rptr
    0.70
     Chapin
    0.60
    AntiForgeryToken
    0.60
    ContentAsync
    0.57
     تضيفلها
    0.55
    DoubleQuotes
    0.53
    tahankan
    0.52
    مؤ
    0.52
    Activations Density 0.001%

    No Known Activations