© 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. 22-RES-MATRYOSHKA-DC
    7. 2578
    Prev
    Next
    INDEX
    Explanations

    prepositions in several contexts, especially in formal or scientific writing

    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
    something
    -0.60
     people
    -0.60
    なもの
    -0.60
     things
    -0.58
     humans
    -0.58
     changes
    -0.56
     decisions
    -0.56
     activities
    -0.56
     transactions
    -0.56
     systems
    -0.55
    POSITIVE LOGITS
     recently
    0.83
     heavily
    0.79
     previously
    0.75
     similarly
    0.75
     lightly
    0.74
     recentemente
    0.74
     freshly
    0.73
     partially
    0.72
     recientemente
    0.72
     randomly
    0.72
    Activations Density 1.020%

    No Known Activations