© 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. 23832
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mat" and related graphical or scientific content

    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
     виправивши
    -1.12
    SequentialGroup
    -1.07
     متعلقه
    -1.02
    таратура
    -0.97
    ніципалі
    -0.94
    ValueGeneration
    -0.94
     препратки
    -0.94
    rungsseite
    -0.94
     Wicidata
    -0.94
     Sigism
    -0.91
    POSITIVE LOGITS
    mat
    1.52
     mat
    1.50
     Mat
    1.45
    Mat
    1.41
     MAT
    1.40
    MAT
    1.33
     Matthews
    1.24
     mats
    1.22
    mats
    1.13
     Mathews
    1.09
    Activations Density 0.017%

    No Known Activations