© 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. 3-RES-MATRYOSHKA-DC
    7. 1235
    Prev
    Next
    INDEX
    Explanations

    The word "the" and the articles "a" and "an".

    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
     hanem
    -0.59
     ciutat
    -0.51
    bury
    -0.50
    Хьажоргаш
    -0.49
    loroethane
    -0.49
     culturally
    -0.49
     campione
    -0.48
     Réponses
    -0.47
     reagiert
    -0.47
     touristes
    -0.46
    POSITIVE LOGITS
    awtextra
    0.84
     pageable
    0.81
    ///</
    0.70
     <<<<<<<<<<<<<<
    0.70
    tagHelperRunner
    0.68
    脚注の使い方
    0.68
     []:
    0.68
    appcompat
    0.67
    ExecutionContext
    0.66
    ValueStyle
    0.66
    Activations Density 0.535%

    No Known Activations