© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements typically seen in programming or coding contexts

    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
    eaking
    -0.59
    Здравствуйте
    -0.59
    Coucou
    -0.57
     Cooke
    -0.56
    ede
    -0.55
     rispet
    -0.54
    Smit
    -0.54
     didik
    -0.53
     ké
    -0.53
    asche
    -0.53
    POSITIVE LOGITS
    writerow
    0.90
     newline
    0.86
    NewLine
    0.82
    GEBURTSDATUM
    0.80
    newline
    0.78
    ChildScrollView
    0.78
    SequentialGroup
    0.74
     milo
    0.72
    Personendaten
    0.72
    তথ্যসূত্র
    0.69
    Activations Density 0.230%

    No Known Activations