© 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. 3-RES-MATRYOSHKA-DC
    7. 45
    Prev
    Next
    INDEX
    Explanations

    words related to quantity and plurality

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.69
     viszont
    -0.57
    はなく
    -0.56
     πως
    -0.56
     которому
    -0.56
     временем
    -0.54
    ly
    -0.54
    infeld
    -0.53
     supérieur
    -0.53
     tôt
    -0.52
    POSITIVE LOGITS
     other
    1.32
     every
    1.30
     each
    1.26
     any
    1.14
    every
    1.14
     dozen
    1.09
     EACH
    1.09
     EVERY
    1.08
     Signalez
    1.07
     تضيفلها
    1.06
    Activations Density 6.208%

    No Known Activations