© 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. 0-CLT-HP
    7. 1847
    Prev
    Next
    INDEX
    Explanations

    operations

    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
     дописавши
    -1.03
     nakalista
    -0.95
    yntaxException
    -0.94
     beginnetje
    -0.92
    verwijspagina
    -0.91
     fieldNum
    -0.90
     intptr
    -0.90
     wireType
    -0.89
    зулта
    -0.89
     ostavi
    -0.88
    POSITIVE LOGITS
     enää
    0.48
     alimentazione
    0.42
     and
    0.41
     lisäksi
    0.41
     achats
    0.40
     métallique
    0.40
     formazione
    0.38
    Eloquent
    0.38
     ellos
    0.38
    Xna
    0.38
    Activations Density 0.067%

    No Known Activations