© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    years

    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
     rumour
    -0.79
    Filmographie
    -0.75
     rumours
    -0.71
    '])){
    -0.69
     tumour
    -0.67
     centre
    -0.67
     rumor
    -0.66
     initialise
    -0.66
    initialise
    -0.66
    bukkit
    -0.66
    POSITIVE LOGITS
     onCreateView
    0.48
     nubes
    0.42
    multirow
    0.40
    alia
    0.40
    UnusedPrivate
    0.40
     postIndex
    0.39
    idig
    0.39
     initComponents
    0.39
    EndInit
    0.38
    omitempty
    0.38
    Activations Density 0.034%

    No Known Activations