© 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. 0-CLT-HP
    7. 1610
    Prev
    Next
    INDEX
    Explanations

    education and policy

    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
    ning
    -0.65
    cel
    -0.61
    aly
    -0.60
    leaf
    -0.60
     découvrez
    -0.57
    ing
    -0.56
    indd
    -0.53
     specchio
    -0.53
    RequiresApi
    -0.50
    ley
    -0.50
    POSITIVE LOGITS
     Bourgoin
    0.73
    StoryboardSegue
    0.67
    homonymie
    0.63
     aprons
    0.59
     caufe
    0.59
    Personensuche
    0.57
     sarees
    0.57
    OGND
    0.55
    seigneur
    0.55
     Khmer
    0.54
    Activations Density 0.280%

    No Known Activations