© 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. 14435
    Prev
    Next
    INDEX
    Explanations

    references to carbonized or charred materials

    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
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.91
     PNP
    -0.86
     pleaſure
    -0.86
     Istri
    -0.85
     Hirst
    -0.85
     Majefty
    -0.84
     betweenstory
    -0.84
     Togo
    -0.83
     Jove
    -0.83
     leaſt
    -0.83
    POSITIVE LOGITS
     Char
    1.24
     CHAR
    1.03
    Char
    1.02
    CHAR
    0.99
     char
    0.94
     Schar
    0.89
     Charlie
    0.79
    chars
    0.78
     Charlene
    0.77
     chars
    0.77
    Activations Density 0.016%

    No Known Activations