© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    coordinates and measurements related to anatomical placement

    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
     Paglinawan
    -0.78
    تقاوى
    -0.73
     defaultstate
    -0.71
     unknownFields
    -0.65
     typelib
    -0.63
    othelioma
    -0.60
     understatement
    -0.59
    GraphicsUnit
    -0.59
     bVar
    -0.57
    cshtml
    -0.55
    POSITIVE LOGITS
    libft
    0.56
    GIVEREF
    0.52
     rác
    0.50
    ่วย
    0.49
    IBOutlet
    0.47
    Carthy
    0.47
     promocional
    0.46
    shutil
    0.45
    Xar
    0.45
     calories
    0.44
    Activations Density 0.002%

    No Known Activations