© 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. 9870
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or terms in a structured document format

    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
    MessageOf
    -0.52
    ynia
    -0.50
    <eos>
    -0.50
     تا
    -0.45
     On
    -0.45
     loro
    -0.44
     noDo
    -0.44
    </em>
    -0.44
     Ketten
    -0.44
     Up
    -0.43
    POSITIVE LOGITS
    Portail
    0.78
    ngdoc
    0.71
     Efq
    0.67
    PageRoute
    0.65
     '\\;'
    0.63
    ImageContext
    0.63
    SOUNDBITE
    0.61
    RectangleBorder
    0.60
     amigurumi
    0.60
     createSprite
    0.60
    Activations Density 0.000%

    No Known Activations