© 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. 67
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ArgsConstructor
    -0.71
    veret
    -0.55
    دانشنامهٔ
    -0.54
     erupted
    -0.52
     nonatomic
    -0.51
    AtIndexPath
    -0.51
     waarop
    -0.50
    IntoConstraints
    -0.50
    GenerationType
    -0.48
    itados
    -0.48
    POSITIVE LOGITS
     you
    0.78
     propOrder
    0.77
     consumers
    0.71
     Consumers
    0.66
    aarrggbb
    0.62
    consumers
    0.60
     Roskov
    0.58
    Consumers
    0.57
     taxpayers
    0.57
     renovate
    0.57
    Activations Density 0.001%

    No Known Activations