© 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. 72945
    Prev
    Next
    INDEX
    Explanations

    fitting

    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
     незавершена
    -0.63
     חיצוניים
    -0.61
     باخ
    -0.56
    setVerticalGroup
    -0.54
     ivelany
    -0.51
    CodedInputStream
    -0.50
     Мексичка
    -0.48
    </thead>
    -0.48
    ншни
    -0.48
    <thead>
    -0.47
    POSITIVE LOGITS
     way
    0.98
     jumping
    0.66
     uintptr
    0.65
     foil
    0.65
     launching
    0.63
     segue
    0.63
     introduction
    0.63
     façon
    0.62
     antidote
    0.60
     spring
    0.58
    Activations Density 0.001%

    No Known Activations