© 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. 32335
    Prev
    Next
    INDEX
    Explanations

    nouns related to mathematical or physical terms, particularly those indicating variables or constants

    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
    httphttps
    -0.71
    发表于
    -0.66
     Gentry
    -0.64
    cticut
    -0.63
    Yun
    -0.62
    itory
    -0.62
    Билгалдахарш
    -0.62
    DataBind
    -0.60
    نیم
    -0.60
    chement
    -0.59
    POSITIVE LOGITS
    kern
    0.77
    ])))
    0.68
    ]^{-
    0.66
    raise
    0.64
    Datuak
    0.60
    stylers
    0.60
    errHandler
    0.59
    ']")
    0.59
    hskip
    0.58
    ')))
    0.56
    Activations Density 0.069%

    No Known Activations