© 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. 20-CLT-HP
    7. 77728
    Prev
    Next
    INDEX
    Explanations

    code or documentation

    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
    Jeografia
    -0.78
     فريبيس
    -0.65
    PreferredItem
    -0.63
    EDEFAULT
    -0.60
     surla
    -0.60
    Autoritní
    -0.59
     الرياضيه
    -0.57
     صوتيه
    -0.57
    клопе
    -0.56
    Personendaten
    -0.56
    POSITIVE LOGITS
    oplayer
    0.59
     ninth
    0.59
     eighth
    0.57
    kunft
    0.54
    eighth
    0.53
    DriverManager
    0.51
     seventh
    0.50
     chấm
    0.50
     ше
    0.49
    ReusableCell
    0.48
    Activations Density 0.000%

    No Known Activations