© 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. 16879
    Prev
    Next
    INDEX
    Explanations

    sections of code or comment blocks that provide various levels of warnings or diagnostics

    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
     an
    -0.48
     alt
    -0.45
    ود
    -0.45
    Tikang
    -0.45
     feet
    -0.43
     Inc
    -0.41
     End
    -0.41
     bid
    -0.40
    .)
    -0.39
     leg
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.91
     consultato
    0.86
    findpost
    0.82
     препратки
    0.82
    \{\\
    0.82
     >=",
    0.81
     Theſe
    0.81
     purpoſe
    0.80
     Chriftian
    0.80
     ſind
    0.79
    Activations Density 0.005%

    No Known Activations