© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    access

    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
    WebVitals
    -0.60
     externi
    -0.54
    sizeCache
    -0.52
    Cyfeiriadau
    -0.52
    وفاته
    -0.49
    [++
    -0.49
    jarati
    -0.48
    precip
    -0.48
    сима
    -0.47
    ană
    -0.47
    POSITIVE LOGITS
     igenom
    0.60
     urma
    0.60
    ors
    0.55
    nsec
    0.51
    bilità
    0.51
     tiennent
    0.50
     works
    0.50
    rawDesc
    0.50
    väg
    0.49
    ntos
    0.49
    Activations Density 0.029%

    No Known Activations