© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6205
    Prev
    Next
    INDEX
    Explanations

    words related to key presses and their effects in handheld electronic devices

    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
    Negative Logits
     abstrato
    -0.58
    BorderFactory
    -0.56
     morreu
    -0.55
     starving
    -0.54
    ChildScrollView
    -0.54
    +#+#
    -0.54
     चीज़ों
    -0.54
     shortages
    -0.52
     chega
    -0.52
    jstor
    -0.52
    POSITIVE LOGITS
     unwanted
    0.63
    undes
    0.61
     undes
    0.57
     ungew
    0.56
    genheiten
    0.52
     uncontrolled
    0.51
    redos
    0.50
    gasse
    0.48
    اریخ
    0.48
    quelles
    0.47
    Activations Density 1.010%

    No Known Activations