© 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. 24-RES-MATRYOSHKA-DC
    7. 1482
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mathematical academic publications, especially those discussing theorems and proofs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    tative
    -0.49
    rektur
    -0.44
    utorial
    -0.44
    oidal
    -0.42
    toria
    -0.42
    exact
    -0.41
    ếp
    -0.41
    soe
    -0.41
    ogia
    -0.40
     conosco
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.83
    Hentet
    0.76
    oa̍t
    0.73
     typelib
    0.72
    DockStyle
    0.71
    Geplaatst
    0.71
    tvguidetime
    0.71
     auroit
    0.70
     únicas
    0.64
    Amicalement
    0.63
    Activations Density 0.565%

    No Known Activations