© 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. 0-CLT-HP
    7. 94999
    Prev
    Next
    INDEX
    Explanations

    open curly bracket

    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
    tableFuture
    -0.59
     PLWABN
    -0.56
    BURGH
    -0.55
     privatization
    -0.52
     Jej
    -0.52
    enterOuterAlt
    -0.52
    ismet
    -0.52
    存于互联网档案馆
    -0.52
     luxem
    -0.51
    Streamer
    -0.51
    POSITIVE LOGITS
     ‘
    0.62
    رشف
    0.61
    dataTables
    0.60
    rawDesc
    0.57
    Бахар
    0.57
    ționale
    0.54
    GEBURTSDATUM
    0.54
    :"-"`
    0.51
     censiti
    0.50
     pinulongan
    0.50
    Activations Density 0.657%

    No Known Activations