© 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. 23452
    Prev
    Next
    INDEX
    Explanations

    numerals or numerical representations in 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
      
    -0.54
    ...
    -0.52
     closed
    -0.51
    …
    -0.50
     the
    -0.49
     related
    -0.48
    </
    -0.47
    ital
    -0.47
    etto
    -0.46
    bim
    -0.46
    POSITIVE LOGITS
     poffe
    0.79
     Roskov
    0.77
     raiſ
    0.76
     purpoſe
    0.76
     ſche
    0.75
     snippetHide
    0.73
     Majefty
    0.72
     ſtate
    0.71
    GraphicsUnit
    0.71
    }],
    0.71
    Activations Density 0.038%

    No Known Activations