© 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. 20-CLT-HP
    7. 72344
    Prev
    Next
    INDEX
    Explanations

    Code and raw text

    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
    sidemargin
    -0.71
    CloseOperation
    -0.64
    AccessorTable
    -0.63
    ----</
    -0.62
    ChildScrollView
    -0.61
    RegressionTest
    -0.61
    __':
    -0.60
     Normdatei
    -0.60
     AssemblyCulture
    -0.59
    Enllaces
    -0.57
    POSITIVE LOGITS
     Northern
    0.77
    Northern
    0.63
     NORTHERN
    0.61
    msgTypes
    0.50
    จุ
    0.46
     lower
    0.46
     Nort
    0.46
    ParameterName
    0.45
     northern
    0.45
    h
    0.45
    Activations Density 0.000%

    No Known Activations