© 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. 26185
    Prev
    Next
    INDEX
    Explanations

    visual representations of data, including graphs, charts, and plots

    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
    ISupport
    -0.79
     ostavi
    -0.72
     Grüßen
    -0.62
    первых
    -0.59
     autorytatywna
    -0.59
    SaveChanges
    -0.54
     utafitiHapana
    -0.54
    ✨:
    -0.53
    modelBuilder
    -0.52
     Meksiku
    -0.52
    POSITIVE LOGITS
    HtmlAttribute
    0.73
    ValueStyle
    0.67
    ttemberg
    0.57
    formKey
    0.56
    enoord
    0.56
    Condol
    0.56
    ovsk
    0.54
    ächter
    0.54
    chyma
    0.54
    AssignableFrom
    0.54
    Activations Density 0.050%

    No Known Activations