© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions related to time and duration in various contexts

    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
     surla
    -0.79
     المعيارى
    -0.63
    KURZBESCHREIBUNG
    -0.63
     Chwiliwch
    -0.60
     мәкалә
    -0.60
     חיצוניים
    -0.59
    сшта
    -0.59
     članak
    -0.59
     Италијани
    -0.58
     Periodic
    -0.57
    POSITIVE LOGITS
     fastest
    0.76
     quickest
    0.73
     schnell
    0.72
    Faster
    0.67
     faster
    0.66
     schnellen
    0.65
     cepat
    0.65
     hızlı
    0.64
    Fastest
    0.64
     quicker
    0.64
    Activations Density 0.320%

    No Known Activations