© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94966
    Prev
    Next
    INDEX
    Explanations

    Measurements and calculations

    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
     itſelf
    -1.06
     Efq
    -1.02
     photolibrary
    -1.01
     fractions
    -0.99
     myſelf
    -0.98
     gallons
    -0.98
     litres
    -0.98
     Jefus
    -0.97
     buckets
    -0.96
     instalments
    -0.96
    POSITIVE LOGITS
     of
    0.90
     in
    0.77
     and
    0.73
    hips
    0.66
     are
    0.65
    .
    0.63
     on
    0.61
    ,
    0.61
     with
    0.58
     to
    0.57
    Activations Density 0.044%

    No Known Activations