© 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. 1-CLT-HP
    7. 15427
    Prev
    Next
    INDEX
    Explanations

    species names

    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
    annas
    -1.26
     myſelf
    -1.15
     themſelves
    -0.97
     itſelf
    -0.90
     Jefus
    -0.88
     Monfieur
    -0.84
     becauſe
    -0.83
     himſelf
    -0.83
     faſt
    -0.81
     leſs
    -0.78
    POSITIVE LOGITS
    e
    0.63
    ">//
    0.59
     autorytatywna
    0.59
    o
    0.57
     Point
    0.57
     发表于
    0.57
    esar
    0.56
     Car
    0.56
    aarrggbb
    0.53
     R
    0.52
    Activations Density 0.048%

    No Known Activations