© 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. 17731
    Prev
    Next
    INDEX
    Explanations

    function definitions and their associated syntax elements

    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
    ἶ
    -0.66
    kedés
    -0.63
     Lara
    -0.62
     WebSocket
    -0.56
     Tatsache
    -0.56
    Olvid
    -0.54
    downcase
    -0.54
    presso
    -0.53
     Gn
    -0.53
    COMP
    -0.53
    POSITIVE LOGITS
     ->
    1.16
    VIAF
    1.00
    sertation
    0.90
    }))
    0.87
    zeria
    0.86
    "):
    0.85
     -->>
    0.84
    MergeFrom
    0.83
    Datuak
    0.82
    })+\
    0.82
    Activations Density 0.009%

    No Known Activations