© 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. 23206
    Prev
    Next
    INDEX
    Explanations

    proper nouns and brand names

    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
    rungsseite
    -0.90
     betweenstory
    -0.85
     AssemblyTitle
    -0.82
     NSCoder
    -0.82
     الرياضيه
    -0.74
    tagHelperRunner
    -0.73
    Portale
    -0.72
    RegressionTest
    -0.71
    ArgsConstructor
    -0.69
     مشين
    -0.69
    POSITIVE LOGITS
    NameInMap
    0.53
    PRF
    0.51
    chlag
    0.45
     mira
    0.41
     Illuminated
    0.40
    UserScript
    0.40
    FormTagHelper
    0.40
     funzion
    0.40
     thương
    0.39
    ’
    0.39
    Activations Density 0.161%

    No Known Activations