© 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. 18-RES-MATRYOSHKA-DC
    7. 29
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and associated verbs

    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.18.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.18.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
    CommandHandler
    -0.64
    dest
    -0.63
    Rüyada
    -0.58
    WithTag
    -0.56
     Gruber
    -0.52
     okaz
    -0.51
    azen
    -0.50
    ALAM
    -0.50
     saling
    -0.50
    กัน
    -0.50
    POSITIVE LOGITS
     would
    1.05
     believe
    1.00
     hope
    0.98
     cannot
    0.96
     had
    0.96
     wouldn
    0.96
     think
    0.96
     have
    0.96
     didn
    0.93
     don
    0.91
    Activations Density 2.131%

    No Known Activations