© 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. 25625
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical terminology related to data structures and instances in a coding context

    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
    تقاوى
    -1.21
     فريبيس
    -1.01
    contentLoaded
    -1.00
     betweenstory
    -1.00
     CreateTagHelper
    -0.99
    +#+#
    -0.96
    RenderAtEndOf
    -0.95
    Geplaatst
    -0.92
    TagMode
    -0.92
     disambiguazione
    -0.91
    POSITIVE LOGITS
    ls
    0.41
    plan
    0.41
     burnt
    0.41
    ila
    0.40
    Hus
    0.40
     Plan
    0.40
    ėl
    0.40
    ts
    0.39
    Plan
    0.39
    fol
    0.38
    Activations Density 1.278%

    No Known Activations