© 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. 26475
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to trust law and beneficiaries' rights

    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
    
    -0.91
    RenderAtEndOf
    -0.88
     lenker
    -0.79
    __':
    -0.77
     propOrder
    -0.77
    matchCondition
    -0.74
     AssemblyCompany
    -0.72
    ]));
    -0.72
    DataSnapshot
    -0.70
    Portale
    -0.70
    POSITIVE LOGITS
     you
    0.64
     contacter
    0.60
    poisson
    0.54
     responsab
    0.54
     things
    0.53
    новид
    0.52
    locationManager
    0.49
     your
    0.48
    jegy
    0.48
     person
    0.48
    Activations Density 0.218%

    No Known Activations