© 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. 15369
    Prev
    Next
    INDEX
    Explanations

    references to code formatting and indentation settings

    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
    {{\
    -0.68
     trans
    -0.58
     http
    -0.55
     AssemblyTitle
    -0.53
     []:
    -0.52
    ศ
    -0.52
     Trans
    -0.51
    Toma
    -0.49
    Nast
    -0.49
    endpush
    -0.48
    POSITIVE LOGITS
     indent
    1.48
    indent
    1.42
    Indent
    1.37
     indentation
    1.20
     indented
    1.09
     houſe
    1.02
     Theſe
    1.01
     Houſe
    0.97
     myſelf
    0.92
     themſelves
    0.92
    Activations Density 0.002%

    No Known Activations