© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court decisions and proceedings

    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
    MENAFN
    -0.62
    fortawesome
    -0.59
    xiu
    -0.58
    devamını
    -0.55
     Schengen
    -0.55
     Methuen
    -0.55
     estrellas
    -0.54
    sense
    -0.54
     poetical
    -0.54
    imperial
    -0.53
    POSITIVE LOGITS
     remanded
    1.14
     remand
    1.10
    MLLoader
    0.78
     newBuilder
    0.66
     intptr
    0.61
    EndInit
    0.59
     للاسماء
    0.58
     ligiloj
    0.57
     AssemblyProduct
    0.57
    LookAnd
    0.55
    Activations Density 0.021%

    No Known Activations