© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30659
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the letter 'n' 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
    Negative Logits
    windowFixed
    -0.99
    DockStyle
    -0.98
    AndEndTag
    -0.98
     $_"
    -0.96
    setVerticalGroup
    -0.93
    ^(@)
    -0.92
     snippetHide
    -0.89
    AsUp
    -0.89
     ―――――
    -0.88
    fillType
    -0.86
    POSITIVE LOGITS
    n
    0.68
     n
    0.57
    N
    0.54
     
    0.51
     S
    0.50
     lo
    0.50
    nant
    0.50
    Vn
    0.50
    tosa
    0.49
    jen
    0.48
    Activations Density 0.005%

    No Known Activations