© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98299
    Prev
    Next
    INDEX
    Explanations

    professional

    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
    ↵↵
    -0.46
    uksia
    -0.40
    ↵
    -0.39
     full
    -0.38
    �
    -0.38
     kunt
    -0.37
    さらに
    -0.36
    あと
    -0.36
     अलावा
    -0.36
    ↵↵↵
    -0.35
    POSITIVE LOGITS
     AssemblyProduct
    1.03
     виправивши
    1.01
    TypedDataSet
    0.98
     Мексичка
    0.94
    PerformLayout
    0.94
     <=",
    0.91
    UnusedPrivate
    0.90
     الرياضيه
    0.90
     snippetHide
    0.90
     Wiktionnaire
    0.90
    Activations Density 0.002%

    No Known Activations