© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4382
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "brief" in various contexts related to legal documents or discussions

    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
    rungsseite
    -0.84
     Schö
    -0.75
     Ellison
    -0.72
    Odon
    -0.68
     Moran
    -0.63
     nucleo
    -0.62
     Osbourne
    -0.62
     Huntingdon
    -0.61
     Singing
    -0.60
     Kela
    -0.60
    POSITIVE LOGITS
     Brief
    1.39
     brief
    1.24
     Briefs
    1.23
     BRIEF
    1.17
    BRIEF
    1.14
    Brief
    1.13
     briefs
    1.13
    brief
    1.09
     brie
    0.89
     Briefing
    0.88
    Activations Density 0.013%

    No Known Activations