© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    the word "My" in various contexts

    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
    ⓧ
    -0.82
     conmigo
    -0.77
     comigo
    -0.71
    virons
    -0.68
     yourselves
    -0.65
     irse
    -0.59
     للاسماء
    -0.59
    Референце
    -0.59
    geschäft
    -0.59
     själva
    -0.59
    POSITIVE LOGITS
    sterious
    0.82
     My
    0.69
     husband
    0.66
     apologies
    0.65
     guess
    0.65
     dear
    0.64
     Mijn
    0.63
    myself
    0.61
     gosh
    0.60
     wife
    0.59
    Activations Density 0.223%

    No Known Activations