© 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. 9661
    Prev
    Next
    INDEX
    Explanations

    references to different worlds or realms, particularly in relation to experiences or conditions in those worlds

    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
    SBATCH
    -0.54
    setVerticalGroup
    -0.52
     ISNI
    -0.51
    ктан
    -0.49
    >//
    -0.49
    stig
    -0.49
     Aguilera
    -0.48
    osgi
    -0.47
    #+#
    -0.46
    styleType
    -0.44
    POSITIVE LOGITS
     realm
    1.02
     realms
    0.96
    realm
    0.94
     Realm
    0.86
     wonderland
    0.82
     Wonderland
    0.81
     houſe
    0.79
     Eſ
    0.77
     uſed
    0.76
     whoſe
    0.75
    Activations Density 0.078%

    No Known Activations