© 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. 22405
    Prev
    Next
    INDEX
    Explanations

    highly technical terms and functions related to programming or code structure

    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
    fromnode
    -0.93
     resourceCulture
    -0.90
    adaptiveStyles
    -0.89
    OGND
    -0.85
     Roskov
    -0.84
    rungsseite
    -0.82
    LookAnd
    -0.82
    Personendaten
    -0.79
    ftagPool
    -0.77
     referenties
    -0.77
    POSITIVE LOGITS
    ency
    0.47
    Thal
    0.47
     fonctionnalités
    0.44
    rels
    0.44
     smör
    0.43
    ÿ
    0.43
    anças
    0.43
    ikat
    0.41
     LOGGER
    0.41
    tya
    0.41
    Activations Density 0.022%

    No Known Activations