© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    uses of the words "we", "you", or "they" followed by a verb of possession or possibility

    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
    Become
    -0.56
    ReusableCell
    -0.54
     Became
    -0.51
    Atoi
    -0.51
     Become
    -0.50
    OptionsMenu
    -0.48
    Occurs
    -0.48
    IntoConstraints
    -0.48
    CANT
    -0.46
     remain
    -0.45
    POSITIVE LOGITS
     having
    1.77
     have
    1.69
     memiliki
    1.57
    having
    1.52
     Having
    1.51
     had
    1.50
    Having
    1.49
     Have
    1.47
    have
    1.46
    Have
    1.45
    Activations Density 1.765%

    No Known Activations