© 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. 17686
    Prev
    Next
    INDEX
    Explanations

    mention of financial transactions or activities

    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
     ویکی‌پدیای
    -1.05
    ^(@)
    -0.94
     myſelf
    -0.85
    ItemBackground
    -0.80
    bibfield
    -0.79
    IUrlHelper
    -0.79
     purpoſe
    -0.77
    twimg
    -0.76
     themſelves
    -0.75
    انگلیسی
    -0.75
    POSITIVE LOGITS
     consumer
    0.45
     offers
    0.44
    厄
    0.43
     offered
    0.43
    el
    0.42
    дь
    0.42
     consumers
    0.42
     citizenship
    0.42
    -
    0.42
    ald
    0.40
    Activations Density 1.048%

    No Known Activations