© 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. 5-CLT-HP
    7. 2263
    Prev
    Next
    INDEX
    Explanations

    Legal, technical documents

    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
    lijf
    -0.54
    Tracce
    -0.51
    FirstResponder
    -0.50
    Bibliograf
    -0.50
     submissions
    -0.47
     सत्यापित
    -0.44
    Bronnen
    -0.44
    Autoritní
    -0.43
     continuance
    -0.43
     Профиль
    -0.43
    POSITIVE LOGITS
     GenerationType
    0.62
     dataSnapshot
    0.59
    fillType
    0.59
     ujednoznacz
    0.57
    Personensuche
    0.56
    rientes
    0.56
    omeness
    0.56
    hoga
    0.55
    gines
    0.54
    tagHelper
    0.53
    Activations Density 0.002%

    No Known Activations