© 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. 1-CLT-HP
    7. 45842
    Prev
    Next
    INDEX
    Explanations

    important

    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
    tvguidetime
    -0.77
    enumii
    -0.68
    VersionUID
    -0.68
    CloseOperation
    -0.68
     Wikispecies
    -0.63
    舺
    -0.62
     EnglishChoose
    -0.60
    Jegyzetek
    -0.60
    
    -0.59
     typelib
    -0.58
    POSITIVE LOGITS
     religious
    0.55
     deity
    0.53
     Buddhist
    0.49
     religiously
    0.48
     As
    0.48
     temple
    0.47
     temples
    0.46
     Тя
    0.45
    As
    0.45
     pilgrimage
    0.44
    Activations Density 0.004%

    No Known Activations