© 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. 4-CLT-HP
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    starting snippets of text

    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
     grasas
    -0.40
    рованной
    -0.40
    mp
    -0.40
     nytt
    -0.39
    vend
    -0.39
     tengah
    -0.39
    mide
    -0.38
    mă
    -0.38
     silenzio
    -0.38
     grasa
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.88
    脚注の使い方
    0.88
    bootstrapcdn
    0.86
     AssemblyCulture
    0.81
     الحره
    0.80
    CodedInputStream
    0.78
     <=",
    0.78
     للاسماء
    0.75
    rrggbb
    0.74
     ddelweddau
    0.74
    Activations Density 0.003%

    No Known Activations