© 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. 26965
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences related to structured data and coding elements

    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
     للاسماء
    -0.87
     ་་
    -0.85
    CodedInputStream
    -0.83
     purpoſe
    -0.79
     ComVisible
    -0.75
     незавершена
    -0.75
    ]")]
    -0.75
     Theſe
    -0.75
    InputBorder
    -0.75
     protoimpl
    -0.74
    POSITIVE LOGITS
    tsch
    0.48
     surla
    0.47
     antworte
    0.46
    צת
    0.43
    setHas
    0.40
    edict
    0.40
     J
    0.39
     hermano
    0.39
    till
    0.38
     etiam
    0.38
    Activations Density 0.002%

    No Known Activations