© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3991
    Prev
    Next
    INDEX
    Explanations

    numerical codes associated with data regions

    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
     الحره
    -0.69
     crossorigin
    -0.56
    Източници
    -0.54
    はじめに
    -0.53
    WriteTagHelper
    -0.51
    ❹
    -0.50
    További
    -0.49
    haf
    -0.49
     classNames
    -0.45
     kaarangay
    -0.45
    POSITIVE LOGITS
    帖最后由
    0.70
     ExecuteAsync
    0.69
    RegressionTest
    0.63
    SourceChecksum
    0.61
     مشين
    0.60
    ruptedException
    0.59
    BeginContext
    0.59
    `,
    0.58
     تضيفلها
    0.57
    >`;
    0.55
    Activations Density 2.159%

    No Known Activations