© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96352
    Prev
    Next
    INDEX
    Explanations

    Measurements and quantities

    np_max-act · 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
    <bos>
    -0.87
    NewUrlParser
    -0.70
     coronation
    -0.52
    Demografie
    -0.48
    unknownFields
    -0.47
    getc
    -0.47
     preference
    -0.47
     pot
    -0.47
     cartel
    -0.46
     तुल
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    0.70
     initComponents
    0.69
     graphiques
    0.68
     numberOfRows
    0.67
     resourceCulture
    0.66
    談社
    0.65
     hígado
    0.64
     avancée
    0.62
     élas
    0.60
     mariée
    0.60
    Activations Density 0.042%

    No Known Activations