© 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. 22453
    Prev
    Next
    INDEX
    Explanations

    elements relating to scientific publications and research data

    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
    GetEnumerator
    -0.67
    principalTable
    -0.63
    دانشنامهٔ
    -0.59
    帖最后由
    -0.55
    awtextra
    -0.54
    ()?;
    -0.51
     argument
    -0.49
     Réponses
    -0.49
    พัน
    -0.45
    花板
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.61
     initComponents
    0.57
     scattata
    0.57
     proposons
    0.57
    спонд
    0.53
    colha
    0.52
    клопе
    0.51
    mogat
    0.50
    ^(@)
    0.50
     schal
    0.50
    Activations Density 0.017%

    No Known Activations