© 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. 30356
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements or data points in a scientific context

    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
    ↵↵
    -0.66
    <eos>
    -0.59
    <?
    -0.52
    <h3>
    -0.46
     L
    -0.42
     #
    -0.41
    ________________
    -0.41
    ér
    -0.40
    </em>
    -0.40
     
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.94
     MainAxisSize
    0.91
    Datuak
    0.91
    principalTable
    0.90
    StoryboardSegue
    0.88
     المعيارى
    0.88
     препратки
    0.82
    تقاوى
    0.81
     onOptions
    0.80
     NSCoder
    0.80
    Activations Density 0.243%

    No Known Activations