© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93378
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     distance
    -2.13
    distance
    -1.91
     Distance
    -1.77
    Distance
    -1.62
     DISTANCE
    -1.51
     distancia
    -1.46
     distances
    -1.45
    DISTANCE
    -1.37
     distanza
    -1.35
     afstand
    -1.27
    POSITIVE LOGITS
    vdash
    0.58
     autorytatywna
    0.52
     tagging
    0.52
     AssemblyProduct
    0.52
     tag
    0.51
    hlmann
    0.50
     tagged
    0.49
     InputDecoration
    0.48
     curling
    0.48
     curve
    0.48
    Activations Density 0.016%

    No Known Activations