© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1747
    Prev
    Next
    INDEX
    Explanations

    references to copyright information and authorship

    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
    apimachinery
    -0.58
    CodeAnalysis
    -0.49
    IBar
    -0.45
    setBounds
    -0.45
    TestingModule
    -0.45
    siapkan
    -0.45
     kereszt
    -0.44
     internationaux
    -0.40
     toiminta
    -0.40
    NoSuch
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.82
     pinulongan
    0.72
     Réponses
    0.69
     kasarigan
    0.68
     :-)
    0.62
     Savior
    0.61
    Viitteet
    0.61
    FTFY
    0.60
    stdc
    0.60
     PhpStorm
    0.60
    Activations Density 0.625%

    No Known Activations