© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 881
    Prev
    Next
    INDEX
    Explanations

    words related to official procedures, particularly those involving addresses and verification

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    -0.96
     مرئيه
    -0.91
     fallait
    -0.88
    AnchorStyles
    -0.84
    IsContent
    -0.81
     passés
    -0.81
     auroit
    -0.81
     تانيه
    -0.78
    RenderAtEndOf
    -0.77
     Waray
    -0.77
    POSITIVE LOGITS
     additionally
    0.64
     furthermore
    0.64
     likewise
    0.59
     moreover
    0.56
     get
    0.52
     un
    0.52
     arrangement
    0.51
     ass
    0.51
     plan
    0.49
    ness
    0.48
    Activations Density 0.154%

    No Known Activations