© 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. 29797
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "desktop"

    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
    Ligações
    -0.69
    ostante
    -0.68
    AddWithValue
    -0.65
    Kanye
    -0.63
    runApp
    -0.61
    afone
    -0.60
    igshid
    -0.60
    |+\
    -0.60
    𝑛
    -0.60
    なく
    -0.59
    POSITIVE LOGITS
     Desktop
    1.30
     DESK
    1.26
    desktop
    1.23
     desktop
    1.22
    Desktop
    1.21
     desktops
    1.14
     Desk
    1.04
    ktop
    1.02
    DESK
    1.02
     desk
    1.01
    Activations Density 0.003%

    No Known Activations