© 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. 12-RES-MATRYOSHKA-DC
    7. 28336
    Prev
    Next
    INDEX
    Explanations

    statistical data related to median age and income within specific demographics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.79
    Xna
    -0.74
    utilisons
    -0.73
    oader
    -0.71
    unately
    -0.68
    KEYCODE
    -0.67
    ✨:
    -0.66
    deauna
    -0.66
     архивлан
    -0.64
    erweise
    -0.63
    POSITIVE LOGITS
     Match
    0.55
    CrossRef
    0.54
    mine
    0.52
    romy
    0.51
     match
    0.49
    jo
    0.48
    name
    0.48
    se
    0.47
     Vann
    0.47
     hasil
    0.47
    Activations Density 0.004%

    No Known Activations