© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76139
    Prev
    Next
    INDEX
    Explanations

    4

    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
    lost
    -0.88
    ^(@)
    -0.79
     '\\;'
    -0.78
    <?
    -0.78
     Poids
    -0.77
    escaped
    -0.76
     Efq
    -0.76
     Rejection
    -0.75
     تكبرها
    -0.75
    ंदीखरीदारी
    -0.74
    POSITIVE LOGITS
     mi
    0.46
     mı
    0.38
     sleep
    0.38
    a
    0.36
    Xna
    0.34
     mia
    0.34
    minHeight
    0.33
    That
    0.31
    EnableWeb
    0.31
    A
    0.31
    Activations Density 0.000%

    No Known Activations