Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40803
    Prev
    Next
    INDEX
    Explanations

    government, legislature

    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
     avoient
    -1.01
     étoient
    -0.98
     feroit
    -0.90
     pouvoit
    -0.85
     auroit
    -0.84
     Efq
    -0.83
    TestingModule
    -0.83
    voorbeeld
    -0.82
     ainfi
    -0.82
     raiſ
    -0.81
    POSITIVE LOGITS
    s
    0.77
     instrument
    0.45
     improvement
    0.40
     Thomas
    0.40
    ся
    0.39
     Fast
    0.39
     group
    0.39
     team
    0.38
     division
    0.38
     Ko
    0.37
    Activations Density 0.617%

    No Known Activations