© 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. 30221
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to property deeds and trusts

    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
     المعيارى
    -0.62
     centrifug
    -0.61
    いる
    -0.60
    ForRow
    -0.59
     Chambres
    -0.58
     Kenji
    -0.58
    InitVars
    -0.58
    lioni
    -0.57
    醐
    -0.57
     agu
    -0.57
    POSITIVE LOGITS
     deed
    1.11
     deeds
    1.08
     Deeds
    1.05
     Deed
    1.04
    deed
    0.81
    MessageTagHelper
    0.71
     Picchu
    0.67
     NgModule
    0.61
    Gesch
    0.59
    цю
    0.58
    Activations Density 0.007%

    No Known Activations