© 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. 30731
    Prev
    Next
    INDEX
    Explanations

    consistent references to specific identifiers or annotations within the text

    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
    ](#
    -1.18
     Tamp
    -0.76
    Emile
    -0.70
    mä
    -0.68
     шпа
    -0.66
     Bep
    -0.66
     Puoi
    -0.65
     equinox
    -0.65
     Pasquale
    -0.65
     TPE
    -0.65
    POSITIVE LOGITS
    aarrggbb
    0.75
     onOptions
    0.66
    awaiter
    0.66
    UnsafeEnabled
    0.65
    InputElement
    0.64
     belegt
    0.64
     ";
    0.63
    XmlAccessorType
    0.61
     ';
    0.61
    Kaynakça
    0.60
    Activations Density 0.002%

    No Known Activations