© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    features of architectural designs and facilities

    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
     فريبيس
    -0.76
     Wicidata
    -0.63
    colar
    -0.60
    󠁴
    -0.58
    tvguidetime
    -0.56
     remp
    -0.56
    tagHelperRunner
    -0.55
     nucléaire
    -0.55
     promet
    -0.53
     المث
    -0.53
    POSITIVE LOGITS
     seating
    0.60
    sbereich
    0.57
     DBNull
    0.54
    WithIdentifier
    0.54
     EventArgs
    0.52
    inetto
    0.52
    HtmlAttribute
    0.51
    instancetype
    0.51
     }^{[
    0.50
     dédi
    0.50
    Activations Density 0.085%

    No Known Activations