© 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. 680
    Prev
    Next
    INDEX
    Explanations

    language used in legal or historical reporting

    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
     MonoBehaviour
    -0.56
    Gön
    -0.56
    Cubit
    -0.56
    GEBURTSDATUM
    -0.55
    ViewFeatures
    -0.51
    mitives
    -0.49
     Picchu
    -0.48
    ManagedBean
    -0.46
     Meksiku
    -0.46
     الرياضيه
    -0.46
    POSITIVE LOGITS
     court
    1.79
     legal
    1.72
     courtroom
    1.67
     courts
    1.65
     judicial
    1.63
     lawyers
    1.62
     lawsuits
    1.59
     lawsuit
    1.55
     litigation
    1.52
     Court
    1.52
    Activations Density 3.422%

    No Known Activations