© 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. 1-CLT-HP
    7. 9197
    Prev
    Next
    INDEX
    Explanations

    database

    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
     nakalista
    -0.70
     initComponents
    -0.64
    :✨
    -0.60
    AndEndTag
    -0.59
     defaultstate
    -0.57
     surla
    -0.55
    TintMode
    -0.54
    IContainer
    -0.52
     Fras
    -0.51
    createNewFile
    -0.51
    POSITIVE LOGITS
    cataly
    0.54
    featureID
    0.53
    Merlin
    0.53
    มาะ
    0.49
    روید
    0.49
     circonstances
    0.47
    LocationManager
    0.47
    ombia
    0.46
    esgue
    0.45
     GenerationType
    0.44
    Activations Density 0.166%

    No Known Activations