© 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. 26003
    Prev
    Next
    INDEX
    Explanations

    sections related to research study methodology and ethical considerations

    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
     seg
    -0.53
    dostęp
    -0.49
    Vegeu
    -0.48
     nødvendig
    -0.48
    üst
    -0.48
    ropriate
    -0.47
    irée
    -0.47
     cœurs
    -0.47
    Hozzáférés
    -0.47
     comércio
    -0.46
    POSITIVE LOGITS
     itſelf
    0.70
    ➟
    0.69
     Etrus
    0.68
     متعلقه
    0.64
     myſelf
    0.62
     Meksiku
    0.62
    EndGlobalSection
    0.59
    хьтан
    0.59
     iſt
    0.58
    +:+
    0.58
    Activations Density 0.002%

    No Known Activations