© 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. 95237
    Prev
    Next
    INDEX
    Explanations

    evolving offerings

    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
     protoimpl
    -0.91
     Мексичка
    -0.91
     pleaſure
    -0.89
     ſmall
    -0.88
     Monfieur
    -0.87
     itſelf
    -0.86
     greateſt
    -0.86
     Chriftian
    -0.85
    ſelves
    -0.84
    ंदीखरीदारी
    -0.83
    POSITIVE LOGITS
     a
    0.68
    y
    0.65
     the
    0.64
     in
    0.63
    a
    0.62
     with
    0.59
    e
    0.58
     to
    0.57
     that
    0.57
     an
    0.52
    Activations Density 0.053%

    No Known Activations