© 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. 22-RES-MATRYOSHKA-DC
    7. 771
    Prev
    Next
    INDEX
    Explanations

    legal language specific to court cases and judgements.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     hearing
    -0.54
    mtliche
    -0.50
    KommentareTeilen
    -0.48
    ISupport
    -0.46
    (#
    -0.46
     accusation
    -0.45
     sentence
    -0.45
    udian
    -0.44
     naik
    -0.44
     granted
    -0.44
    POSITIVE LOGITS
     Roskov
    0.73
     jurisprudence
    0.71
     numerus
    0.69
    IUrlHelper
    0.68
    tagHelperRunner
    0.66
     AssemblyCompany
    0.66
    prechung
    0.64
    Bioaccumulative
    0.64
     Apply
    0.63
     Lehre
    0.63
    Activations Density 1.550%

    No Known Activations