© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    per

    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
    +:+
    -0.56
    he
    -0.54
    i
    -0.54
    Hozzáférés
    -0.54
    let
    -0.52
    CppCodeGen
    -0.52
    DotNetBar
    -0.52
    msgSender
    -0.50
    con
    -0.49
    it
    -0.48
    POSITIVE LOGITS
    loyee
    0.62
    NUMX
    0.62
    expandindo
    0.61
    rentices
    0.56
    islative
    0.56
     betweenstory
    0.56
    knecht
    0.55
    elfare
    0.52
    esterday
    0.52
    olesale
    0.52
    Activations Density 0.001%

    No Known Activations