© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2618
    Prev
    Next
    INDEX
    Explanations

    while

    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
    Going
    -0.57
     Going
    -0.55
     seda
    -0.50
    发表于
    -0.49
    原始内容存档于
    -0.49
     GOING
    -0.48
    comparing
    -0.48
    ❋
    -0.47
     renewing
    -0.47
     rearranging
    -0.46
    POSITIVE LOGITS
     also
    0.81
     meanwhile
    0.75
    Бахар
    0.67
     simultaneously
    0.61
    IsContent
    0.59
     likewise
    0.59
    ]")]
    0.58
     TAMBIÉN
    0.58
     of
    0.57
     conversely
    0.57
    Activations Density 0.002%

    No Known Activations