© 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. 30290
    Prev
    Next
    INDEX
    Explanations

    expressions and descriptions related to data structures and memory layouts in programming

    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
    InputBorder
    -0.49
     eikä
    -0.46
     liso
    -0.45
     """",
    -0.44
    فت
    -0.44
    šanas
    -0.43
    limit
    -0.41
     bestem
    -0.41
     Antioch
    -0.41
     remet
    -0.41
    POSITIVE LOGITS
    upported
    0.66
    Попис
    0.65
    ResumeLayout
    0.62
    usermodel
    0.57
    erai
    0.56
    ingway
    0.55
    ISupport
    0.54
     barometer
    0.54
    FECTION
    0.54
    SPATH
    0.54
    Activations Density 0.037%

    No Known Activations