© 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. 24276
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables in a document

    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
     Moyen
    -0.48
     surla
    -0.47
     EoL
    -0.44
     noDo
    -0.43
     ComVisible
    -0.43
     Ada
    -0.42
    oque
    -0.41
    SALT
    -0.40
    RTHOOK
    -0.39
    Vía
    -0.39
    POSITIVE LOGITS
     المعيارى
    0.91
     bezeichneter
    0.88
    RenderAtEndOf
    0.76
    tvguidetime
    0.72
    存于互联网档案馆
    0.69
    NullException
    0.69
     reaſon
    0.68
     purpoſe
    0.66
     connexes
    0.64
    PerformLayout
    0.61
    Activations Density 0.019%

    No Known Activations