© 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. 30977
    Prev
    Next
    INDEX
    Explanations

    mathematical or structural elements represented by curly braces

    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
     kasarigan
    -0.88
    PreferredItem
    -0.87
    AddTagHelper
    -0.80
    Искәрмәләр
    -0.72
    Geplaatst
    -0.69
     RIPRODUZIONE
    -0.69
    تقاوى
    -0.68
    izator
    -0.67
    NUMX
    -0.66
    quelize
    -0.66
    POSITIVE LOGITS
    +#+
    0.71
     ***!
    0.50
    hasMoreElements
    0.44
     presentes
    0.44
    findpost
    0.44
    Revenir
    0.43
    zak
    0.43
     present
    0.41
    con
    0.40
    em
    0.40
    Activations Density 0.012%

    No Known Activations