© 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. 24987
    Prev
    Next
    INDEX
    Explanations

    terms related to legal limitations or constraints

    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
    Negative Logits
     Gole
    -0.85
    Hozzáférés
    -0.83
    complexContent
    -0.79
     Ayers
    -0.76
    Им
    -0.74
     memin
    -0.73
     Lakers
    -0.73
     Solver
    -0.73
    quelize
    -0.72
    cemia
    -0.72
    POSITIVE LOGITS
    сылкі
    0.78
    ricted
    0.78
     Rousseau
    0.78
     Restrictions
    0.78
     Cors
    0.72
     Restriction
    0.70
     restrictions
    0.69
    uesday
    0.68
    rictive
    0.68
     restriction
    0.66
    Activations Density 0.013%

    No Known Activations