© 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-RES-MATRYOSHKA-DC
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    references to the word "which," indicating it detects or focuses on instances where "which" is used

    oai_token-act-pair · gpt-4.1-nano
    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
     disambiguazione
    -0.99
    UserScript
    -0.83
     kasarigan
    -0.82
    LookAnd
    -0.82
    verständlich
    -0.81
     betweenstory
    -0.78
     daß
    -0.76
     disponibilités
    -0.76
     duquel
    -0.75
     ujednoznacz
    -0.74
    POSITIVE LOGITS
     It
    0.55
    enterOuterAlt
    0.53
    RunAsync
    0.47
    ̵
    0.47
     fend
    0.46
     They
    0.44
    界
    0.44
     vantaggio
    0.43
     than
    0.42
     dovrebbero
    0.42
    Activations Density 0.076%

    No Known Activations