© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3198
    Prev
    Next
    INDEX
    Explanations

    and

    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
    SharedDtor
    -0.66
    новниш
    -0.56
     présidenti
    -0.56
     تضيفلها
    -0.56
    Contrast
    -0.53
    setVerticalGroup
    -0.53
     fondi
    -0.53
     scolaires
    -0.52
    gehe
    -0.51
    tagHelper
    -0.51
    POSITIVE LOGITS
    اریخ
    0.61
     robbed
    0.60
     Sikhs
    0.60
     capturing
    0.59
     Palestinians
    0.56
     seized
    0.55
     desec
    0.55
     Afghans
    0.54
     atheists
    0.54
     snatched
    0.54
    Activations Density 0.006%

    No Known Activations