© 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. 1-RES-MATRYOSHKA-DC
    7. 242
    Prev
    Next
    INDEX
    Explanations

    references to the current time or moments indicating immediacy

    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
    WithIOException
    -0.71
     disambiguazione
    -0.69
    instancetype
    -0.69
     jsPsych
    -0.62
     vulgaires
    -0.60
    ेशा
    -0.60
    []=$
    -0.59
     onFailure
    -0.58
     mList
    -0.57
    InjectAttribute
    -0.57
    POSITIVE LOGITS
     now
    3.84
    now
    3.38
     Now
    3.17
    Now
    3.05
     NOW
    3.00
    NOW
    2.81
     ahora
    2.77
     agora
    2.70
     here
    2.64
     maintenant
    2.63
    Activations Density 0.539%

    No Known Activations