© 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. 16049
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests or calls to action relating to legislative or governmental processes

    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
    rungsseite
    -0.69
    出版年
    -0.60
    例句
    -0.58
     continúas
    -0.52
    +");
    -0.52
    maketitle
    -0.52
     coser
    -0.52
     pro
    -0.51
     complex
    -0.51
     marketing
    -0.50
    POSITIVE LOGITS
     mergeFrom
    0.64
     bonté
    0.60
     TGA
    0.56
    diques
    0.54
    DockStyle
    0.54
    DDB
    0.54
     ioutil
    0.53
    OpenHelper
    0.52
     mør
    0.51
    vlá
    0.50
    Activations Density 0.039%

    No Known Activations