© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we," indicating a focus on collective authorship or perspective

    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
     محفوظة
    -0.71
    дём
    -0.54
    mos
    -0.53
    sik
    -0.52
    chka
    -0.52
    pes
    -0.51
     pem
    -0.51
     complementary
    -0.51
     laten
    -0.50
    чё
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.77
    antaranya
    0.75
     vPvB
    0.75
     raiſ
    0.74
    χρι
    0.72
    IndentedString
    0.71
     Huguen
    0.71
     EconPapers
    0.70
    unnitel
    0.69
     betweenstory
    0.69
    Activations Density 0.046%

    No Known Activations