© 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. 2408
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "you" and related pronouns (we, us)

    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
     ComVisible
    -0.71
    ArrowToggle
    -0.68
     uintptr
    -0.65
     Wiktionnaire
    -0.62
    autorest
    -0.58
    mobileqq
    -0.57
     صوتيه
    -0.55
     XCTest
    -0.54
    InjectAttribute
    -0.53
    WriteBarrier
    -0.52
    POSITIVE LOGITS
     nakalista
    0.59
     curent
    0.54
    alite
    0.52
     actionPerformed
    0.50
    endung
    0.50
     DbSet
    0.50
     savon
    0.49
    ButterKnife
    0.48
    JNIEnv
    0.48
    entie
    0.48
    Activations Density 0.057%

    No Known Activations