© 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. 95235
    Prev
    Next
    INDEX
    Explanations

    Sticking out, irregular occurrence

    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
     myſelf
    -0.88
     Jefus
    -0.85
     Inſ
    -0.85
     Monfieur
    -0.82
     Shakspeare
    -0.82
     itſelf
    -0.81
     propOrder
    -0.81
     Eſ
    -0.80
     Theſe
    -0.80
     Beſ
    -0.79
    POSITIVE LOGITS
    fer
    0.64
    nd
    0.62
    n
    0.59
    th
    0.59
    ne
    0.56
    nom
    0.56
    ën
    0.56
    na
    0.55
    -
    0.55
    nter
    0.54
    Activations Density 1.294%

    No Known Activations