© 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. 28268
    Prev
    Next
    INDEX
    Explanations

    terms related to endogenous factors or components

    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
    Parcelize
    -0.84
     unmute
    -0.81
    !*\
    -0.78
     Kamer
    -0.71
    /*
    -0.69
    íslu
    -0.69
     Pew
    -0.67
     Audiodateien
    -0.67
     Vra
    -0.66
     Smar
    -0.65
    POSITIVE LOGITS
    ogenous
    0.94
    prende
    0.69
     SES
    0.68
     endogenous
    0.61
    *-*-
    0.61
     inds
    0.60
    Eleg
    0.60
    teborg
    0.60
     Bergman
    0.60
     canister
    0.60
    Activations Density 0.002%

    No Known Activations