© 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. 18-RES-MATRYOSHKA-DC
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    various code snippets and structural programming elements like template declarations, preprocessor directives, array indexing with brackets, or references to th

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    __':
    -1.34
    __":
    -1.24
     مشين
    -1.23
    ]")]
    -1.22
    SBATCH
    -1.21
    "):
    -1.20
    =$?
    -1.20
    ',
    -1.19
    >\<^
    -1.19
    FTFY
    -1.17
    POSITIVE LOGITS
      
    1.05
    and
    1.03
    to
    0.94
    has
    0.94
    is
    0.93
    I
    0.91
       
    0.91
    in
    0.90
     ,
    0.90
    for
    0.90
    Activations Density 3.066%

    No Known Activations