© 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. 20-CLT-HP
    7. 73432
    Prev
    Next
    INDEX
    Explanations

    code/genetics jargon

    np_max-act-logits · 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
    ftagPool
    -0.52
    LayoutStyle
    -0.50
     ligation
    -0.48
    CppMethod
    -0.48
    Dane
    -0.47
    abase
    -0.47
     ioutil
    -0.46
     Besoin
    -0.46
    rogly
    -0.46
     Syed
    -0.45
    POSITIVE LOGITS
    (!__
    0.48
    koz
    0.48
    fromnode
    0.48
    μάτων
    0.47
    marvin
    0.47
     scrim
    0.47
    ătate
    0.46
    routeProvider
    0.46
     Romana
    0.46
    جمه
    0.45
    Activations Density 0.002%

    No Known Activations