© 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. 76635
    Prev
    Next
    INDEX
    Explanations

    modern

    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
    GraphicsUnit
    -0.93
     CreateTagHelper
    -0.92
    SourceChecksum
    -0.86
    abestanden
    -0.84
    ⓧ
    -0.84
    WriteTagHelper
    -0.83
     ostavi
    -0.82
    tagHelperRunner
    -0.81
    ftagPool
    -0.81
    Rüyada
    -0.81
    POSITIVE LOGITS
     creature
    0.72
     am
    0.60
     modern
    0.60
    amen
    0.54
     mod
    0.54
    am
    0.50
     ام
    0.50
     basic
    0.48
     amen
    0.46
    modern
    0.45
    Activations Density 0.001%

    No Known Activations