© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38415
    Prev
    Next
    INDEX
    Explanations

    neighbor

    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
     neighbours
    -1.27
     neighbors
    -1.22
     neighbour
    -1.15
    neighbor
    -1.15
     neighbor
    -1.12
     voisins
    -1.05
    neighbour
    -1.05
     Neighbors
    -1.05
    neighbours
    -1.04
     neighboring
    -1.02
    POSITIVE LOGITS
    ed
    0.51
    pes
    0.51
    ing
    0.49
     dan
    0.45
     patron
    0.45
     wor
    0.44
     pos
    0.44
     dif
    0.43
     du
    0.42
     st
    0.41
    Activations Density 0.092%

    No Known Activations