© 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. 24-RES-MATRYOSHKA-DC
    7. 8
    Prev
    Next
    INDEX
    Explanations

    court documents involving an appeal and review of errors regarding the trial

    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.24.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.24.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
    ImageContext
    -0.79
     disambiguazione
    -0.77
     Paglinawan
    -0.75
     AssemblyVersion
    -0.74
    责任编辑
    -0.69
     AssemblyTitle
    -0.66
    ientôt
    -0.65
     TextInputType
    -0.65
    Datuak
    -0.63
     personalise
    -0.63
    POSITIVE LOGITS
     appellate
    0.71
     sua
    0.65
     remand
    0.64
     summary
    0.63
     Rule
    0.63
     motion
    0.59
     counsel
    0.59
     motions
    0.59
     disposi
    0.59
     defendant
    0.57
    Activations Density 8.310%

    No Known Activations