© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21013
    Prev
    Next
    INDEX
    Explanations

    references to the second person, specifically "you" and "I", indicating a focus on personal connection and individual agency

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    InputTagHelper
    -0.73
     Turkmenistan
    -0.72
     Theſe
    -0.67
    aguya
    -0.65
     Sachin
    -0.64
     Schwal
    -0.63
    UserScript
    -0.60
     Wandel
    -0.60
     capilar
    -0.59
     Alca
    -0.59
    POSITIVE LOGITS
     that
    0.74
     ComVisible
    0.71
    esModule
    0.67
    CppMethod
    0.66
     Taktlose
    0.66
    koning
    0.66
    RemoveField
    0.64
     चीज़ों
    0.61
    that
    0.58
    opengl
    0.58
    Activations Density 0.096%

    No Known Activations