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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9679
    Prev
    Next
    INDEX
    Explanations

    chemistry, location, timezones

    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
    cay
    -0.83
    CloseOperation
    -0.75
    Хьажоргаш
    -0.74
    oul
    -0.72
    CreateMap
    -0.68
    ModelAdmin
    -0.68
    LANTA
    -0.66
    ContentAlignment
    -0.66
    VIAF
    -0.65
    webElementGuid
    -0.65
    POSITIVE LOGITS
    !("{
    0.42
     terciopelo
    0.37
     hennes
    0.36
    findpost
    0.35
    dotenv
    0.34
    MetaObject
    0.34
     atriz
    0.34
    Batt
    0.33
    ↵↵
    0.33
     הס
    0.33
    Activations Density 0.044%

    No Known Activations