© 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. 26216
    Prev
    Next
    INDEX
    Explanations

    variables and symbols commonly used in mathematical or graph-theoretical contexts

    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
     propOrder
    -1.16
    帖最后由
    -1.05
     purpoſe
    -0.99
     Roskov
    -0.97
     ſever
    -0.91
     myſelf
    -0.91
    yntaxException
    -0.91
     raiſ
    -0.90
    WithIOException
    -0.90
     reaſon
    -0.90
    POSITIVE LOGITS
     Sub
    0.64
    _
    0.60
     ca
    0.58
     Wach
    0.55
     present
    0.55
     Who
    0.52
     I
    0.52
     –
    0.51
     pop
    0.50
     Pop
    0.49
    Activations Density 0.014%

    No Known Activations