© 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. 77492
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     charges
    -1.24
     charge
    -1.12
     Charges
    -1.11
    Charges
    -1.04
     Charge
    -1.04
     charged
    -0.95
    Charge
    -0.93
    charge
    -0.90
     CHARGE
    -0.89
    charges
    -0.86
    POSITIVE LOGITS
    InjectAttribute
    0.65
    vitt
    0.56
     незавершена
    0.51
    Tembelea
    0.50
     álcool
    0.47
     métallique
    0.47
    PyExc
    0.46
    GraphicsUnit
    0.46
    ̈́
    0.45
     voors
    0.44
    Activations Density 0.003%

    No Known Activations