© 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. 4-CLT-HP
    7. 3391
    Prev
    Next
    INDEX
    Explanations

    by

    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
    tagHelperRunner
    -0.86
     متعلقه
    -0.81
    Personendaten
    -0.77
     stället
    -0.69
    SharedDtor
    -0.68
     ujednoznacz
    -0.68
     تانيه
    -0.68
     épaules
    -0.67
     genoux
    -0.64
     apporté
    -0.63
    POSITIVE LOGITS
     taxes
    0.68
     bribes
    0.66
     tax
    0.66
     subscriptions
    0.63
     deductions
    0.62
     levies
    0.61
     money
    0.61
     grants
    0.60
     $
    0.60
     gains
    0.59
    Activations Density 0.002%

    No Known Activations