© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10882
    Prev
    Next
    INDEX
    Explanations

    super

    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
    ThroughAttribute
    -0.62
    StructEnd
    -0.61
     eventdata
    -0.58
    IUrlHelper
    -0.55
     Wicidata
    -0.54
     BorderSide
    -0.52
     whistling
    -0.52
    ंदीखरीदारी
    -0.51
    elemField
    -0.51
     SDLK
    -0.50
    POSITIVE LOGITS
    новниш
    0.56
    cop
    0.53
    "}>
    0.52
     marge
    0.51
    gra
    0.50
    Bibliograf
    0.49
    )}_
    0.49
     }],
    0.47
     argc
    0.47
    runApp
    0.47
    Activations Density 0.018%

    No Known Activations