© 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. 97072
    Prev
    Next
    INDEX
    Explanations

    relegated

    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
     للاسماء
    -0.60
    Hauptartikel
    -0.59
    istique
    -0.58
     Movie
    -0.57
    bootstrapcdn
    -0.57
    Filmografie
    -0.56
    ]})
    -0.56
    ]**
    -0.56
    ंदीखरीदारी
    -0.55
     ProtoMessage
    -0.54
    POSITIVE LOGITS
     Cæsar
    0.56
    พอ
    0.48
     AppModule
    0.48
     gradova
    0.47
    MediaStore
    0.47
    middels
    0.47
     افتراض
    0.47
     useHistory
    0.46
    acamata
    0.46
     Sekund
    0.45
    Activations Density 0.271%

    No Known Activations