© 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. 72763
    Prev
    Next
    INDEX
    Explanations

    *

    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
    </thead>
    -0.62
    bootstrapcdn
    -0.57
     Penh
    -0.55
    obr
    -0.48
     AssemblyTitle
    -0.47
     Ethical
    -0.46
    Ethical
    -0.46
    Ethics
    -0.46
     Ethics
    -0.46
    ScopeManager
    -0.45
    POSITIVE LOGITS
     util
    0.60
     Immanuel
    0.59
     Raw
    0.54
    ERVIEW
    0.53
     tele
    0.53
     jadx
    0.52
     Kant
    0.52
     propOrder
    0.51
     vPvB
    0.51
     de
    0.50
    Activations Density 0.000%

    No Known Activations