© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    HTML navigation elements

    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
     chó
    -0.81
    RegistryLite
    -0.77
     Umum
    -0.75
     Normdatei
    -0.72
     Boone
    -0.72
    tvguidetime
    -0.70
     typelib
    -0.69
    parametrize
    -0.69
     gmina
    -0.69
    openha
    -0.68
    POSITIVE LOGITS
    nav
    1.28
     nav
    1.18
    Nav
    1.09
     Nav
    1.09
     NavController
    0.97
     NAV
    0.81
    NAV
    0.71
     XK
    0.70
    ==='
    0.67
    NavController
    0.66
    Activations Density 0.002%

    No Known Activations