© 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. 77432
    Prev
    Next
    INDEX
    Explanations

    years/dates from 1600s

    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
     eighteenth
    -0.69
     Propriet
    -0.64
     Royale
    -0.62
     VOC
    -0.60
    eigh
    -0.60
     XVII
    -0.57
     XVIII
    -0.56
     Eighteenth
    -0.54
    Ancien
    -0.52
     Courant
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.52
    omitempty
    0.47
     geme
    0.47
    korn
    0.47
    ValueStyle
    0.46
    SerializedName
    0.45
    rails
    0.45
    Rails
    0.45
     <=",
    0.44
    evich
    0.42
    Activations Density 0.004%

    No Known Activations