© 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. 21051
    Prev
    Next
    INDEX
    Explanations

    references to angels and related concepts

    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
    Negative Logits
     combineReducers
    -0.86
    verwijspagina
    -0.82
     LSM
    -0.81
     Jir
    -0.79
     Convex
    -0.78
     reccom
    -0.78
    paravant
    -0.78
     Eccle
    -0.78
    antMatchers
    -0.77
     Pharisees
    -0.77
    POSITIVE LOGITS
     Angel
    1.59
     Angels
    1.48
    Angels
    1.39
    Angel
    1.38
     angel
    1.31
     ANGEL
    1.29
    angels
    1.24
     angels
    1.23
    angel
    1.16
    ANGEL
    0.97
    Activations Density 0.004%

    No Known Activations