© 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. 5-CLT-HP
    4. 94929
    Prev
    Next
    INDEX
    Explanations

    of

    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
     others
    -0.70
     businesses
    -0.66
     other
    -0.65
     candidates
    -0.64
     many
    -0.64
     hotels
    -0.63
     restaurants
    -0.61
    ')")
    -0.61
     shops
    -0.61
     clients
    -0.60
    POSITIVE LOGITS
     a
    0.76
     an
    0.72
     vœux
    0.62
     coordonnées
    0.61
     bénéfices
    0.61
     âmes
    0.59
     bienfaits
    0.59
     renseignements
    0.59
     inconvénients
    0.58
     preuves
    0.57
    Activations Density 0.001%

    No Known Activations