© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18567
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and courtroom dynamics

    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
    Filmografie
    -0.81
    ArrowToggle
    -0.81
     незавершена
    -0.77
     Majefty
    -0.75
     Jefus
    -0.69
     CreateTagHelper
    -0.69
     SDLK
    -0.68
     pleaſure
    -0.68
     Monfieur
    -0.68
     becauſe
    -0.67
    POSITIVE LOGITS
     resourceCulture
    0.66
     вот
    0.47
    contentLoaded
    0.47
     
    0.45
    CUSS
    0.45
     pan
    0.43
    <eos>
    0.43
     nahilalakip
    0.42
    uh
    0.42
    ugin
    0.41
    Activations Density 0.110%

    No Known Activations