© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3130
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time, usually in months, with surrounding numbers

    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
    Negative Logits
     years
    -0.74
     decade
    -0.66
     year
    -0.63
     años
    -0.59
    years
    -0.55
    decade
    -0.54
    year
    -0.53
     Jahren
    -0.50
     Jahr
    -0.49
    Ids
    -0.49
    POSITIVE LOGITS
     Month
    1.33
     Monthly
    1.32
     monthly
    1.31
    Monthly
    1.26
    Month
    1.21
    month
    1.16
    monthly
    1.16
     month
    1.16
    MONTH
    1.16
     months
    1.14
    Activations Density 0.226%

    No Known Activations