© 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. 25741
    Prev
    Next
    INDEX
    Explanations

    references to leakage or leaks 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
    Not in Any Lists

    No Comments

    Negative Logits
    mtext
    -0.67
     Bronson
    -0.63
    DCC
    -0.61
     terang
    -0.60
    mathbf
    -0.59
     Tro
    -0.57
     Cartwright
    -0.56
     Desc
    -0.56
     reckoning
    -0.56
    +#+
    -0.54
    POSITIVE LOGITS
     leaks
    1.35
     leak
    1.30
     Leak
    1.30
     leakage
    1.27
     Leaks
    1.23
     Leakage
    1.19
    leak
    1.18
    Leak
    1.10
    Leaks
    1.10
     leaking
    1.05
    Activations Density 0.006%

    No Known Activations