© 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. 26031
    Prev
    Next
    INDEX
    Explanations

    references to legal cases involving the United States

    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
    LookAnd
    -0.83
    PreferredItem
    -0.71
    OGND
    -0.65
    cèse
    -0.63
     transfieras
    -0.63
     protoimpl
    -0.59
    audiovisuel
    -0.59
    TemporalType
    -0.57
    OrNil
    -0.57
     Meksiku
    -0.57
    POSITIVE LOGITS
    omento
    0.64
    STRUCTIONS
    0.64
    charm
    0.61
    uerto
    0.59
     Werth
    0.59
     Colours
    0.55
    beten
    0.54
     favourite
    0.54
    ucson
    0.54
    TAX
    0.54
    Activations Density 0.005%

    No Known Activations