© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    visual representations of measurement scales or indicators

    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
    thirsty
    -0.54
     tanı
    -0.52
     lautet
    -0.52
     inspiração
    -0.52
    BaseType
    -0.51
     virtù
    -0.49
     tasche
    -0.47
    outline
    -0.47
     copertura
    -0.47
     Diſ
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    1.10
     Roskov
    0.78
    AxisAlignment
    0.77
     ISNI
    0.77
    windowFixed
    0.75
    NgModule
    0.69
     GenerationType
    0.69
    dotenv
    0.68
    httphttps
    0.68
    makeText
    0.68
    Activations Density 0.000%

    No Known Activations