© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41057
    Prev
    Next
    INDEX
    Explanations

    quantitative

    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
     engraçadas
    -0.88
     épaules
    -0.88
     marquées
    -0.84
     réguli
    -0.84
     oreilles
    -0.84
     larmes
    -0.82
     enfans
    -0.82
     avoient
    -0.81
     prisonniers
    -0.81
     réfrig
    -0.81
    POSITIVE LOGITS
    e
    0.63
    ists
    0.59
    s
    0.57
    ia
    0.51
    ist
    0.49
    ی
    0.48
     affairs
    0.46
    ised
    0.46
     concerns
    0.45
     resources
    0.44
    Activations Density 0.353%

    No Known Activations