© 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. 9654
    Prev
    Next
    INDEX
    Explanations

    architectural elements and features in structures

    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
     Signalez
    -0.58
     nakalista
    -0.54
    хьтан
    -0.54
     سير
    -0.52
     FACILITY
    -0.52
     Facility
    -0.50
    SURFACE
    -0.50
    EndInit
    -0.50
    태
    -0.50
     EconPapers
    -0.50
    POSITIVE LOGITS
    TintMode
    0.71
     smtplib
    0.65
    onAttach
    0.61
    Попис
    0.55
    WidgetItem
    0.51
     obecnie
    0.50
    RegistryLite
    0.49
     AdapterView
    0.49
     useRouter
    0.49
    thias
    0.48
    Activations Density 0.037%

    No Known Activations