© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16220
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting markers in text

    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
    AnchorStyles
    -0.53
    tvguidetime
    -0.49
    tadır
    -0.48
    gehend
    -0.47
    gwt
    -0.47
    íncia
    -0.47
    footnote
    -0.47
    misu
    -0.47
    aryen
    -0.47
    localVar
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.69
     صوتيه
    0.61
     Vikipedi
    0.55
    MigrationBuilder
    0.55
    sidemargin
    0.54
     الرياضيه
    0.51
    swire
    0.51
    ArrowToggle
    0.49
    ❹
    0.47
    StoryboardSegue
    0.46
    Activations Density 0.001%

    No Known Activations