© 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. 20-CLT-HP
    7. 74870
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · 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
    RegressionTest
    -0.63
    󠁴
    -0.60
     kaynağından
    -0.59
     فريبيس
    -0.57
     doInBackground
    -0.56
     Altogether
    -0.55
    AsUp
    -0.54
     незавершена
    -0.53
    łku
    -0.52
     fermés
    -0.52
    POSITIVE LOGITS
     at
    2.42
     tại
    1.13
     At
    0.98
    At
    0.92
    at
    0.89
     AT
    0.82
     	e
    0.80
     ở
    0.68
     atx
    0.59
    getValueAt
    0.58
    Activations Density 0.004%

    No Known Activations