© 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. 31895
    Prev
    Next
    INDEX
    Explanations

    hash or preprocessor directives commonly used in programming code

    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
    ))->
    -0.59
     CanadaChoose
    -0.53
    :])
    -0.52
    vron
    -0.52
    )->
    -0.52
    RenderAtEndOf
    -0.52
    üng
    -0.50
     nahilalakip
    -0.50
     vueltas
    -0.50
     '':
    -0.50
    POSITIVE LOGITS
    fjspx
    0.60
     الاطلاع
    0.59
    CloseOperation
    0.59
    iastes
    0.59
    ensement
    0.56
     jadx
    0.56
    LEncoder
    0.56
     createState
    0.54
     ComVisible
    0.54
    istani
    0.54
    Activations Density 0.011%

    No Known Activations