© 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. 12-RES-MATRYOSHKA-DC
    7. 29524
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal conditions and provisions regarding eligibility and approvals

    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
     heller
    -0.50
     umana
    -0.50
     professionali
    -0.50
     måneder
    -0.49
     femininas
    -0.49
     umano
    -0.46
     henkil
    -0.45
     vru
    -0.45
    ⓘ
    -0.45
     Ender
    -0.45
    POSITIVE LOGITS
     становника
    0.62
     ligiloj
    0.59
     الحره
    0.59
     Meksiku
    0.59
    SharedCtor
    0.59
     cherchés
    0.56
    ropriate
    0.56
    rrggbb
    0.56
     insuffisamment
    0.55
     Italijanski
    0.55
    Activations Density 0.044%

    No Known Activations