© 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. 474
    Prev
    Next
    INDEX
    Explanations

    academic/technical texts

    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
     for
    -0.58
    ure
    -0.54
     the
    -0.52
    list
    -0.50
     is
    -0.48
    :
    -0.48
     list
    -0.47
     with
    -0.46
     a
    -0.46
     gri
    -0.45
    POSITIVE LOGITS
    :✨
    0.89
     Italijanski
    0.71
    ScopeManager
    0.71
    Попис
    0.69
     الدولى
    0.68
    InstrumentedTest
    0.66
    Personendaten
    0.64
    aarrggbb
    0.63
    Tikang
    0.63
     Италијани
    0.63
    Activations Density 0.002%

    No Known Activations