© 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. 91872
    Prev
    Next
    INDEX
    Explanations

    Code, tech, or names

    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
    تقاوى
    -1.26
     Мексичка
    -1.26
     ujednoznacz
    -1.17
    '},
    -1.17
    AndEndTag
    -1.10
     typelib
    -1.10
     disambiguazione
    -1.09
    "},
    -1.09
    :✨
    -1.08
     cherchés
    -1.03
    POSITIVE LOGITS
    ↵↵
    0.67
    ↵
    0.50
    w
    0.47
    ↵↵↵
    0.47
     -
    0.47
    _
    0.45
    we
    0.44
    ma
    0.43
    ke
    0.43
     meyd
    0.42
    Activations Density 0.004%

    No Known Activations