© 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. 234
    Prev
    Next
    INDEX
    Explanations

    sentences about screws, materials they're made of, and their connection to bone

    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
     vérit
    -0.92
     déchir
    -0.90
     leçons
    -0.85
     supérieurs
    -0.81
     ainfi
    -0.80
     rigue
    -0.80
     gouvernements
    -0.79
     côtés
    -0.79
     ostensibly
    -0.79
     plufieurs
    -0.78
    POSITIVE LOGITS
    Nowadays
    0.92
     Nowadays
    0.86
    }^{+\
    0.85
     nowadays
    0.84
     planification
    0.77
     transversal
    0.77
     punctual
    0.76
    lenght
    0.74
     advices
    0.72
     confort
    0.71
    Activations Density 5.544%

    No Known Activations