© 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. 32079
    Prev
    Next
    INDEX
    Explanations

    terms related to naming and renaming entities or organizations

    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
     ProtoMessage
    -0.91
    tableFuture
    -0.85
     CreateTagHelper
    -0.84
    AddTagHelper
    -0.83
     للمعارف
    -0.81
     transfieras
    -0.75
    setVerticalGroup
    -0.74
    InputBorder
    -0.74
     defaultstate
    -0.74
    InjectAttribute
    -0.72
    POSITIVE LOGITS
     Vierge
    0.54
     Popp
    0.53
    ticle
    0.48
     nicio
    0.47
    pædia
    0.46
     vierge
    0.45
     cohé
    0.44
     figliu
    0.43
    gæ
    0.43
     coward
    0.42
    Activations Density 0.033%

    No Known Activations