© 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. 1312
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "you" and related pronouns like "I" and "me" in questions or conditional clauses

    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
    entibus
    -0.57
     ostavi
    -0.57
     finnas
    -0.54
    ViewFeatures
    -0.54
    ungeon
    -0.51
    FormTagHelper
    -0.51
    有一定
    -0.50
     gehad
    -0.50
     avoient
    -0.50
    有一定的
    -0.50
    POSITIVE LOGITS
     behave
    0.97
     behaves
    0.90
     handled
    0.89
     interact
    0.88
     handle
    0.88
     comport
    0.82
     interacts
    0.82
     react
    0.82
    看待
    0.81
     handling
    0.80
    Activations Density 0.674%

    No Known Activations