© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 914
    Prev
    Next
    INDEX
    Explanations

    legal or governmental language about rights, powers, and authority

    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
    ISupport
    -0.77
    Geplaatst
    -0.74
    PerformLayout
    -0.68
    новниш
    -0.68
    djangoproject
    -0.65
    ReusableCell
    -0.63
    ValueStyle
    -0.62
     للمعارف
    -0.61
    MessageTagHelper
    -0.58
    UrlResolution
    -0.56
    POSITIVE LOGITS
     authority
    1.45
     power
    1.41
     powers
    1.33
    power
    1.25
    authority
    1.20
    powers
    1.18
     delegated
    1.12
    Power
    1.09
     Power
    1.06
    Powers
    1.04
    Activations Density 1.383%

    No Known Activations