© 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. 457
    Prev
    Next
    INDEX
    Explanations

    field

    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
     समीक्षक
    -0.94
     ujednoznacz
    -0.85
    #+#
    -0.80
    Portale
    -0.79
     onOptions
    -0.79
    ValueGeneration
    -0.77
    Приятного
    -0.76
     >=",
    -0.75
     itſelf
    -0.74
    IVEREF
    -0.71
    POSITIVE LOGITS
    ↵
    0.61
    ↵↵
    0.54
      
    0.45
    7
    0.43
    ing
    0.42
    8
    0.41
     I
    0.41
    manship
    0.40
    3
    0.40
     (
    0.40
    Activations Density 0.022%

    No Known Activations