© 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. 14562
    Prev
    Next
    INDEX
    Explanations

    CSS selectors and properties

    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
    ísimo
    -0.48
    ⓘ
    -0.47
    VIAF
    -0.46
    hwar
    -0.45
    wanan
    -0.44
     “
    -0.44
     a
    -0.44
     Black
    -0.44
     '';
    -0.42
    CloseOperation
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.81
    +#+#
    0.81
    ьаж
    0.77
    &:
    0.76
    hawatir
    0.76
    __((
    0.76
    contentLoaded
    0.75
    Hochspringen
    0.74
    saraba
    0.73
    '&:
    0.73
    Activations Density 0.002%

    No Known Activations