© 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. 2-RES-MATRYOSHKA-DC
    7. 3593
    Prev
    Next
    INDEX
    Explanations

    sentences that specify a time reference or point of occurrence

    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
     after
    -1.52
    after
    -1.45
    After
    -1.42
     After
    -1.39
     dopo
    -1.33
     AFTER
    -1.23
    AFTER
    -1.21
     Dopo
    -1.16
    Dopo
    -1.12
     après
    -1.11
    POSITIVE LOGITS
     before
    1.19
    before
    1.00
    paravant
    0.97
     Before
    0.95
     før
    0.94
    BEFORE
    0.94
    Before
    0.88
     sebelum
    0.87
     precede
    0.86
     befo
    0.86
    Activations Density 0.061%

    No Known Activations