© 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. 5-CLT-HP
    7. 370
    Prev
    Next
    INDEX
    Explanations

    technical documents/web pages

    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
    хьтан
    -0.74
    NUMX
    -0.65
    Życiorys
    -0.65
     recensement
    -0.64
    GEBURTSDATUM
    -0.64
     chi̍t
    -0.61
    uxxxx
    -0.60
    
    -0.58
    IVEREF
    -0.57
    webElementXpaths
    -0.57
    POSITIVE LOGITS
    activity
    0.54
     activity
    0.52
    size
    0.52
    Activity
    0.47
    to
    0.44
     noten
    0.43
     ACTIVITY
    0.42
     |=
    0.42
     BeautifulSoup
    0.41
    sizes
    0.40
    Activations Density 0.002%

    No Known Activations