© 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. 28527
    Prev
    Next
    INDEX
    Explanations

    repeated sequences within a structured data format

    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
     faſt
    -0.98
     reaſon
    -0.91
     itſelf
    -0.91
     ainfi
    -0.90
     ſon
    -0.88
     ſche
    -0.87
     myſelf
    -0.87
     unſ
    -0.86
     whereof
    -0.85
     ſever
    -0.85
    POSITIVE LOGITS
     
    0.59
     am
    0.50
    ↵
    0.48
     str
    0.46
     The
    0.46
    ு
    0.45
     New
    0.45
    ↵↵
    0.44
     d
    0.44
     Home
    0.43
    Activations Density 0.007%

    No Known Activations