© 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. 26834
    Prev
    Next
    INDEX
    Explanations

    code snippets related to class and data structure definitions

    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
    </strong>
    -0.54
     pass
    -0.53
    ua
    -0.52
    </b>
    -0.51
     Fire
    -0.50
     Multi
    -0.49
     Ge
    -0.49
     
    -0.47
     multi
    -0.47
    ↵↵
    -0.47
    POSITIVE LOGITS
     onAnimation
    0.98
    AndEndTag
    0.95
     مشين
    0.94
    WithIOException
    0.88
    Демографія
    0.84
    исленность
    0.81
    ViewFeatures
    0.80
    IntoConstraints
    0.80
    setVerticalGroup
    0.79
     onCancelled
    0.79
    Activations Density 0.124%

    No Known Activations