© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1652
    Prev
    Next
    INDEX
    Explanations

    find out

    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
     "
    -0.59
     
    -0.59
     a
    -0.56
     A
    -0.55
     I
    -0.52
     or
    -0.52
     “
    -0.50
    ro
    -0.48
     and
    -0.47
    out
    -0.47
    POSITIVE LOGITS
    AndEndTag
    1.09
     propOrder
    1.02
     Paglinawan
    1.01
    =$?
    1.00
    findpost
    1.00
     referenties
    0.99
    Personendaten
    0.98
     Shakspeare
    0.98
     resourceCulture
    0.97
     للمعارف
    0.96
    Activations Density 0.213%

    No Known Activations