© 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. 29544
    Prev
    Next
    INDEX
    Explanations

    coding patterns related to configuration parameters and settings

    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
    脚注の使い方
    -0.76
     للاسماء
    -0.66
    })));
    -0.62
    RenderAtEndOf
    -0.62
    ."],
    -0.60
    RegressionTest
    -0.59
     صوتيه
    -0.59
    tamol
    -0.58
    MessageTagHelper
    -0.58
    RunWith
    -0.57
    POSITIVE LOGITS
    enumi
    0.51
    onViewCreated
    0.49
    zenten
    0.47
     rentals
    0.47
     respeito
    0.47
    IntoConstraints
    0.46
    WithMany
    0.46
    cookieParser
    0.45
     fornito
    0.44
    obus
    0.44
    Activations Density 0.100%

    No Known Activations