© 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. 4-CLT-HP
    7. 1353
    Prev
    Next
    INDEX
    Explanations

    that

    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
    ναν
    -0.49
     himo
    -0.49
    şik
    -0.48
     ingenieros
    -0.45
    Filmografie
    -0.44
     kasarigan
    -0.44
    beat
    -0.44
     diseñadores
    -0.43
    수
    -0.42
    дцать
    -0.42
    POSITIVE LOGITS
    Lähteet
    0.77
    AntiForgeryToken
    0.76
    </tfoot>
    0.68
    AccessorTable
    0.67
    
    0.65
    клопе
    0.64
     maximizing
    0.64
     becauſe
    0.64
    OrBuilder
    0.62
     extracting
    0.61
    Activations Density 0.007%

    No Known Activations