© 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. 42867
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
     للاسماء
    -0.99
     itſelf
    -0.85
     AssemblyProduct
    -0.84
     Monfieur
    -0.84
     Efq
    -0.83
     faſt
    -0.82
     myſelf
    -0.82
     للمعارف
    -0.81
     OFDb
    -0.80
     يتيمه
    -0.79
    POSITIVE LOGITS
    ↵
    0.56
     (
    0.50
    .
    0.48
    '
    0.47
    <eos>
    0.44
     with
    0.44
    (
    0.43
    ↵↵↵↵
    0.42
    C
    0.41
    \
    0.41
    Activations Density 0.731%

    No Known Activations