© 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. 30646
    Prev
    Next
    INDEX
    Explanations

    the letter "c" throughout the document

    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
     houſe
    -0.80
     neceff
    -0.69
     Jefus
    -0.67
     purpoſe
    -0.67
     chofe
    -0.66
     beſt
    -0.66
     ſtand
    -0.65
     pleaſure
    -0.62
     ſta
    -0.60
     poffe
    -0.60
    POSITIVE LOGITS
    c
    0.89
    IntoConstraints
    0.85
     c
    0.74
    ecore
    0.72
    principalColumn
    0.63
     AssemblyCulture
    0.63
    存于互联网档案馆
    0.61
    unhofer
    0.60
    ':
    0.59
    iNdEx
    0.58
    Activations Density 0.001%

    No Known Activations