© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     about
    -0.84
    about
    -0.57
     About
    -0.52
     ABOUT
    -0.52
     riguardo
    -0.51
    About
    -0.50
     tentang
    -0.50
    зер
    -0.44
     respeito
    -0.44
     proposito
    -0.42
    POSITIVE LOGITS
     the
    1.10
    Autoritní
    0.85
    abetes
    0.75
     ویکی‌پدی
    0.73
    IndentedString
    0.66
    :]:
    0.66
    DockStyle
    0.66
    :");
    0.64
     autorytatywna
    0.63
     this
    0.63
    Activations Density 0.002%

    No Known Activations