© 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. 9679
    Prev
    Next
    INDEX
    Explanations

    references to personal opinion or perspective

    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
     tartalomajánló
    -0.63
     Gret
    -0.62
    uttavia
    -0.56
    RenderAtEndOf
    -0.55
     bezeichneter
    -0.49
    ეთ
    -0.49
     SCO
    -0.48
    osted
    -0.48
    Гри
    -0.48
     дописавши
    -0.48
    POSITIVE LOGITS
    Jeografia
    0.72
     typelib
    0.61
     Савезне
    0.59
     AttributeSet
    0.58
    Javadoc
    0.54
    argout
    0.53
     geslacht
    0.52
    AntiForgeryToken
    0.51
    HasAnnotation
    0.51
    mphony
    0.50
    Activations Density 0.092%

    No Known Activations