© 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. 1846
    Prev
    Next
    INDEX
    Explanations

    dates and numbers, especially years

    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
     архивлан
    -0.76
     autorytatywna
    -0.63
     vPvB
    -0.61
     Wikimedijinoj
    -0.59
    NamedQueries
    -0.59
     مواليد
    -0.58
     wikipagina
    -0.58
    ":[{
    -0.57
     RSSSF
    -0.57
     navideña
    -0.56
    POSITIVE LOGITS
    CloseOperation
    0.59
    BitmapFactory
    0.59
     fe
    0.56
     Fe
    0.51
     major
    0.45
     Tuesday
    0.45
     Mon
    0.44
     zw
    0.44
    URLException
    0.44
    addPreferredGap
    0.43
    Activations Density 0.195%

    No Known Activations