© 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. 2-RES-MATRYOSHKA-DC
    7. 4527
    Prev
    Next
    INDEX
    Explanations

    phrases involving the infinitive "to" followed by a verb

    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
    ArgsConstructor
    -0.63
    колеп
    -0.62
    TestingModule
    -0.61
     typelib
    -0.60
    ValueGeneration
    -0.60
     fubject
    -0.59
     AUSSI
    -0.57
    antaranya
    -0.57
    Становништво
    -0.57
     Audiodateien
    -0.56
    POSITIVE LOGITS
     versucht
    0.85
     attempts
    0.78
     attempting
    0.73
     attempt
    0.69
     attempted
    0.68
    试图
    0.68
     tentando
    0.67
    trying
    0.66
     tryna
    0.65
    attempts
    0.64
    Activations Density 0.121%

    No Known Activations