© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92792
    Prev
    Next
    INDEX
    Explanations

    sports competitions

    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
    Bowl
    -0.85
     Bowl
    -0.77
    bowl
    -0.70
     dieux
    -0.61
    iella
    -0.60
    sweet
    -0.60
     bowl
    -0.59
     Sweet
    -0.59
     genoux
    -0.58
    Sweet
    -0.57
    POSITIVE LOGITS
    ly
    0.91
    ness
    0.80
    fraid
    0.62
    est
    0.58
    tened
    0.58
    ened
    0.58
    aneous
    0.57
    tably
    0.57
    ure
    0.51
    adays
    0.51
    Activations Density 1.694%

    No Known Activations