© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    metadata elements related to academic articles, such as author names and titles

    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
    кза
    -0.46
     here
    -0.43
    ști
    -0.39
    ंस
    -0.39
     ung
    -0.38
     Eins
    -0.37
     ό
    -0.36
     all
    -0.36
     immer
    -0.35
     At
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    1.34
    rungsseite
    1.01
     समीक्षक
    1.01
    ValueStyle
    0.96
    elemField
    0.96
    MigrationBuilder
    0.95
     <<<<<<<<<<<<<<
    0.94
     bezeichneter
    0.92
     يتيمه
    0.91
     дописавши
    0.90
    Activations Density 0.148%

    No Known Activations