© 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. 0-CLT-HP
    7. 43974
    Prev
    Next
    INDEX
    Explanations

    people

    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
     subordinates
    -1.01
     assistants
    -0.95
     advisers
    -0.90
     allies
    -0.87
     consultants
    -0.86
     helpers
    -0.83
     minions
    -0.81
     recruits
    -0.80
     informants
    -0.79
     aides
    -0.78
    POSITIVE LOGITS
     виправивши
    0.74
    tead
    0.61
     délais
    0.61
     épaules
    0.57
    AutoField
    0.53
    Tikang
    0.52
    :+:
    0.52
    fony
    0.50
     hombros
    0.49
    por
    0.49
    Activations Density 0.089%

    No Known Activations