© 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. 0-CLT-HP
    7. 43547
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
     authorities
    -0.94
     AUTHORITIES
    -0.81
    authorities
    -0.76
     Authorities
    -0.74
     disambiguazione
    -0.70
     Industries
    -0.69
    Autoritní
    -0.69
     nakalista
    -0.68
    oa̍t
    -0.68
     industries
    -0.66
    POSITIVE LOGITS
    hips
    0.70
    hip
    0.50
     رأ
    0.45
    erent
    0.42
    teps
    0.42
    es
    0.42
    ates
    0.41
    Segoe
    0.40
    erci
    0.40
    unsqueeze
    0.40
    Activations Density 0.264%

    No Known Activations