© 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. 5049
    Prev
    Next
    INDEX
    Explanations

    is

    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
     in
    -0.79
    存于互联网档案馆
    -0.70
    estris
    -0.62
    antaine
    -0.61
     dalam
    -0.61
    zerű
    -0.60
    msgTypes
    -0.59
    eterminate
    -0.59
    volvement
    -0.58
    IntoConstraints
    -0.57
    POSITIVE LOGITS
    enerys
    0.46
    ########.
    0.44
     counters
    0.43
     lenker
    0.43
     extends
    0.42
    msgSender
    0.42
     masculin
    0.41
     gyhoeddwyd
    0.41
    HtmlAttribute
    0.41
     relate
    0.41
    Activations Density 0.012%

    No Known Activations