© 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. 6207
    Prev
    Next
    INDEX
    Explanations

    references to specific studies, data analyses, or educational content related to public health and safety

    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
     itſelf
    -1.07
     myſelf
    -1.01
     ་་
    -0.87
    ſelves
    -0.84
     themſelves
    -0.84
     ſche
    -0.84
     Corsica
    -0.83
     Reſ
    -0.83
    ſelf
    -0.82
     himſelf
    -0.82
    POSITIVE LOGITS
     der
    0.42
     de
    0.41
     South
    0.41
    contentLoaded
    0.40
    面
    0.40
     }}-
    0.39
     unknownFields
    0.38
     C
    0.38
    TagHelpers
    0.37
     h
    0.37
    Activations Density 2.594%

    No Known Activations