© 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. 17115
    Prev
    Next
    INDEX
    Explanations

    configuration settings and parameters related to data sources and their properties

    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
     незавершена
    -0.93
    ########.
    -0.88
    esModule
    -0.82
     AssemblyCulture
    -0.81
    UrlResolution
    -0.79
    DockStyle
    -0.77
    webElement
    -0.77
     ComVisible
    -0.76
    styleType
    -0.75
     BoxDecoration
    -0.72
    POSITIVE LOGITS
     idle
    0.51
    idle
    0.49
     roving
    0.47
    Idle
    0.47
    initialValue
    0.46
     ART
    0.44
     aggressively
    0.42
     spawn
    0.42
     Fiore
    0.42
    maxsize
    0.42
    Activations Density 0.108%

    No Known Activations