© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    markdown image link syntax

    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
    rungsseite
    -1.38
     Manson
    -0.96
    +#+
    -0.93
     Chwiliwch
    -0.93
     onCreateView
    -0.83
    rouvez
    -0.82
     autorytatywna
    -0.81
    erobic
    -0.81
     Herod
    -0.79
    '.$
    -0.77
    POSITIVE LOGITS
    ](
    0.98
    )](
    0.78
    fraid
    0.69
    httphttps
    0.67
    )}^{
    0.65
     _(
    0.62
    lank
    0.60
    "](
    0.60
    fully
    0.58
    voked
    0.58
    Activations Density 0.013%

    No Known Activations