© 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. 4-CLT-HP
    7. 955
    Prev
    Next
    INDEX
    Explanations

    Biographies

    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
     autorytatywna
    -1.08
    archiviato
    -1.00
     Roskov
    -0.99
     myſelf
    -0.97
     Мексичка
    -0.96
     незавершена
    -0.94
    تقاوى
    -0.94
    rungsseite
    -0.92
    Portale
    -0.91
    expandindo
    -0.89
    POSITIVE LOGITS
     
    0.43
    class
    0.40
    脯
    0.39
    addSubview
    0.38
     Su
    0.36
    add
    0.36
     détaillés
    0.36
    ="
    0.36
    盹
    0.35
    Class
    0.35
    Activations Density 0.023%

    No Known Activations