© 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. 10752
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or sequences, particularly in letters or character strings

    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
     Theſe
    -0.95
    ,:);
    -0.94
     houſe
    -0.85
    ₂)
    -0.84
     dieß
    -0.82
    — 
    -0.80
     myſelf
    -0.80
     ་་
    -0.78
     ―――――
    -0.78
    )»
    -0.77
    POSITIVE LOGITS
    enegro
    0.81
    ckner
    0.63
    t
    0.58
     t
    0.57
    ST
    0.54
     piatta
    0.54
     GenerationType
    0.54
    r
    0.54
    RRRR
    0.53
     x
    0.53
    Activations Density 0.004%

    No Known Activations