© 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. 32221
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the 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
    GEBURTSDATUM
    -0.69
     mergeFrom
    -0.62
     AssemblyProduct
    -0.61
     trajets
    -0.59
    priate
    -0.59
    ptonshire
    -0.57
    Jeografia
    -0.56
     Predic
    -0.55
     lautet
    -0.54
    σιμοποι
    -0.54
    POSITIVE LOGITS
    preventDefault
    0.66
    PickerController
    0.57
    setVerticalGroup
    0.55
    ]")]
    0.53
    parsedMessage
    0.51
    ArrowToggle
    0.49
    ="@+
    0.48
    хозяй
    0.47
    Ữ
    0.47
     />';
    0.46
    Activations Density 0.010%

    No Known Activations