© 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. 12-RES-MATRYOSHKA-DC
    7. 14687
    Prev
    Next
    INDEX
    Explanations

    mentions of age or duration expressed in months

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    o
    -0.81
     dě
    -0.73
     referenties
    -0.66
     useNavigate
    -0.63
    a
    -0.62
     Kre
    -0.59
    ?>
    -0.58
     Pave
    -0.58
     églises
    -0.57
     држа
    -0.56
    POSITIVE LOGITS
    getMonth
    0.89
    Months
    0.89
    months
    0.88
     Months
    0.87
    moth
    0.83
     months
    0.82
     Munster
    0.81
     MotionEvent
    0.80
     Mons
    0.80
     MONTHS
    0.80
    Activations Density 0.018%

    No Known Activations