© 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. 31822
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    AppCompat
    -0.63
    nacht
    -0.62
    juvant
    -0.60
    PRESA
    -0.55
    habi
    -0.52
    0
    -0.52
     Bartol
    -0.52
    rauch
    -0.50
    2
    -0.50
    μπ
    -0.49
    POSITIVE LOGITS
    ']))
    0.91
    yntaxException
    0.84
     BIBSYS
    0.80
     kasarigan
    0.79
    بوابة
    0.77
    enumi
    0.77
    "}>
    0.75
    "])
    0.75
    lgari
    0.73
    IsInitialized
    0.72
    Activations Density 0.094%

    No Known Activations