© 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. 22838
    Prev
    Next
    INDEX
    Explanations

    mentions of structural characteristics 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
    </caption>
    -0.93
    ChildScrollView
    -0.92
    </tfoot>
    -0.88
    ]='\
    -0.88
    ImageContext
    -0.87
     HasFactory
    -0.86
     InputDecoration
    -0.84
    stit
    -0.84
    UseVisualStyle
    -0.84
    "</
    -0.84
    POSITIVE LOGITS
    7
    0.61
    6
    0.59
    al
    0.57
    й
    0.57
    9
    0.56
     Zal
    0.52
    yal
    0.51
    hift
    0.51
     SAL
    0.51
    ial
    0.50
    Activations Density 0.004%

    No Known Activations