© 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. 5-CLT-HP
    7. 806
    Prev
    Next
    INDEX
    Explanations

    year

    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
     Konferenz
    -0.59
     autorytatywna
    -0.57
    цездатний
    -0.56
    reloadData
    -0.52
    `,
    -0.52
    sont
    -0.50
    couvrez
    -0.49
     propagate
    -0.48
     grab
    -0.48
    tableFuture
    -0.48
    POSITIVE LOGITS
    SuccessListener
    0.57
    lights
    0.50
    ns
    0.50
    ling
    0.49
    tan
    0.48
    men
    0.46
    marks
    0.46
    akes
    0.46
    ned
    0.46
    ning
    0.46
    Activations Density 0.001%

    No Known Activations