© 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. 0-CLT-HP
    7. 94024
    Prev
    Next
    INDEX
    Explanations

    quantities/numbers

    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
    eight
    -0.79
     démocr
    -0.79
     nine
    -0.78
     médicaux
    -0.77
     six
    -0.76
     judiciaire
    -0.75
     ouvriers
    -0.75
    six
    -0.75
     fidèles
    -0.74
     supérieurs
    -0.73
    POSITIVE LOGITS
    ly
    1.18
    teen
    1.17
    s
    1.15
    teenth
    0.96
    ness
    0.93
    ties
    0.89
    n
    0.89
    es
    0.87
    ses
    0.86
    ning
    0.84
    Activations Density 0.066%

    No Known Activations