© 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. 980
    Prev
    Next
    INDEX
    Explanations

    instances of the words "I", "you", "we" followed by a verb of thinking or watching.

    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
    /**
    -0.51
     asser
    -0.47
    rifice
    -0.47
    を出す
    -0.47
    rückt
    -0.47
     shoots
    -0.47
    nasse
    -0.46
    cmu
    -0.46
    Kariera
    -0.46
    athione
    -0.45
    POSITIVE LOGITS
     reading
    1.64
     read
    1.48
     watching
    1.45
    reading
    1.30
     watch
    1.26
     viewing
    1.25
     listening
    1.24
     reads
    1.24
    watching
    1.21
    Reading
    1.20
    Activations Density 1.536%

    No Known Activations