© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    references to inmates and their requests or grievances within a correctional context

    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
    afficheront
    -0.73
     afield
    -0.69
    InitVars
    -0.69
     intptr
    -0.67
    haustible
    -0.67
    KommentareTeilen
    -0.63
     Taktlose
    -0.63
    ERVE
    -0.62
     Carsten
    -0.62
    RegistryLite
    -0.62
    POSITIVE LOGITS
     inmate
    1.22
     inmates
    1.15
    Prison
    1.15
     prison
    1.14
     Prison
    1.14
     prisons
    1.04
    prison
    1.00
     prisoners
    0.98
     Prisons
    0.96
     prisoner
    0.93
    Activations Density 0.359%

    No Known Activations