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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 406
    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
     vérit
    -0.68
     larmes
    -0.68
     sanitarias
    -0.66
     nuages
    -0.62
     judiciales
    -0.61
     gezet
    -0.61
     déclarations
    -0.60
     bénéfices
    -0.59
     épaules
    -0.59
     genoux
    -0.59
    POSITIVE LOGITS
    OGND
    0.60
    ModelAdmin
    0.58
     animals
    0.57
    sizeCache
    0.56
     OT
    0.56
     kasarigan
    0.56
     guests
    0.56
     riders
    0.55
     Ker
    0.55
    BeginContext
    0.54
    Activations Density 0.025%

    No Known Activations