© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22109
    Prev
    Next
    INDEX
    Explanations

    references to the month of October and its variations

    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
     Wiseman
    -0.81
     SMD
    -0.77
     CMP
    -0.75
     Xmas
    -0.71
     geodes
    -0.71
     Noma
    -0.71
     Christmas
    -0.70
     christmas
    -0.69
    idenav
    -0.69
    EMBRE
    -0.67
    POSITIVE LOGITS
     AssemblyCulture
    1.00
     OCTOBER
    0.98
     October
    0.94
    TemporalType
    0.94
    OCTOBER
    0.91
     octubre
    0.91
    kháu
    0.90
    October
    0.90
     Dernière
    0.89
     propOrder
    0.89
    Activations Density 0.020%

    No Known Activations