© 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. 95095
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    y
    -0.66
    t
    -0.63
     Authority
    -0.62
    er
    -0.60
    i
    -0.60
     Authorization
    -0.59
    ه
    -0.55
     authorization
    -0.54
     attenuated
    -0.52
    a
    -0.50
    POSITIVE LOGITS
     propOrder
    0.94
    Билгалдахарш
    0.74
     otomatig
    0.71
    AndEndTag
    0.69
    ografija
    0.68
    省市镇
    0.65
    yntaxException
    0.61
     betweenstory
    0.61
    sibilities
    0.60
    nastics
    0.60
    Activations Density 0.617%

    No Known Activations