© 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. 22-RES-MATRYOSHKA-DC
    7. 1669
    Prev
    Next
    INDEX
    Explanations

    words indicating time, especially the present or near past

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     later
    -0.85
     lately
    -0.82
     recently
    -0.81
     vroeger
    -0.79
     nowadays
    -0.79
     później
    -0.79
     actuellement
    -0.76
     obecnie
    -0.75
     später
    -0.75
     senere
    -0.75
    POSITIVE LOGITS
     generations
    1.12
     generation
    0.97
     incarnation
    0.91
    generation
    0.90
     iteration
    0.90
    itisation
    0.89
     iterations
    0.89
     تضيفلها
    0.76
     stages
    0.76
    WebVitals
    0.75
    Activations Density 0.778%

    No Known Activations