© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    technical language related to programming and 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
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.68
    TestingModule
    -0.64
    artifactId
    -0.63
     "..\..\..\
    -0.62
    mybatisplus
    -0.56
     Pristupljeno
    -0.55
    慢慢的
    -0.54
    SourceChecksum
    -0.54
    nonatomic
    -0.53
    PageFactory
    -0.51
    POSITIVE LOGITS
    ^(@)
    0.78
     reaſon
    0.77
     ſeveral
    0.75
    <_>
    0.73
     themſelves
    0.72
     ſtre
    0.72
    becue
    0.71
     ſen
    0.71
     perſon
    0.71
     purpoſe
    0.70
    Activations Density 5.361%

    No Known Activations