© 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. 4-CLT-HP
    7. 1023
    Prev
    Next
    INDEX
    Explanations

    people

    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
     was
    -0.53
    charCodeAt
    -0.50
    檚
    -0.48
     kellett
    -0.47
     gql
    -0.46
    Was
    -0.45
     censiti
    -0.45
     géographique
    -0.45
    UnusedPrivate
    -0.44
    gpl
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.84
    AntiForgeryToken
    0.71
     initComponents
    0.66
     ſind
    0.65
     know
    0.64
     onOptions
    0.63
     uſe
    0.62
    prefixer
    0.60
     understand
    0.60
     Baillargeon
    0.60
    Activations Density 0.003%

    No Known Activations