© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    searching/querying

    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
     Reference
    -0.98
     reference
    -0.96
    Reference
    -0.91
    reference
    -0.90
     riferimento
    -0.87
     référence
    -0.85
     Theſe
    -0.79
     REFERENCE
    -0.78
     Shakspeare
    -0.75
     referência
    -0.69
    POSITIVE LOGITS
    眶
    0.57
     def
    0.54
     >=",
    0.54
     censiti
    0.54
    fiets
    0.54
    óm
    0.53
    nelse
    0.52
    belea
    0.50
     str
    0.50
    aderie
    0.49
    Activations Density 0.105%

    No Known Activations