© 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. 4-CLT-HP
    7. 827
    Prev
    Next
    INDEX
    Explanations

    community

    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
     disponibilités
    -0.66
     ostavi
    -0.63
     estekak
    -0.60
    ponses
    -0.59
     Infórmanos
    -0.56
    ंदीखरीदारी
    -0.54
    fromnode
    -0.54
     sociali
    -0.54
     totalSupply
    -0.52
     VIAF
    -0.50
    POSITIVE LOGITS
    webElementGuid
    0.60
    awaiter
    0.54
     Chi
    0.51
     John
    0.48
    ropol
    0.48
     Pan
    0.47
     Action
    0.47
     Unit
    0.47
     Color
    0.47
     Big
    0.46
    Activations Density 0.004%

    No Known Activations