© 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. 32154
    Prev
    Next
    INDEX
    Explanations

    section or subsection references in a document

    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
     scho
    -0.62
    ành
    -0.60
    detectChanges
    -0.59
     Bradshaw
    -0.59
     sympy
    -0.59
     volantes
    -0.58
    Scho
    -0.57
     Chuan
    -0.57
     Scho
    -0.56
    HANG
    -0.56
    POSITIVE LOGITS
    subsec
    1.27
     subsection
    1.02
    subsection
    0.93
     Subsection
    0.86
     становника
    0.78
    IVEREF
    0.73
    Jereo
    0.73
     subsections
    0.72
    ✨:
    0.71
     مشين
    0.71
    Activations Density 0.004%

    No Known Activations