© 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. 2-RES-MATRYOSHKA-DC
    7. 7488
    Prev
    Next
    INDEX
    Explanations

    the word "sh" and its variants

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    selaer
    -0.68
    TagHelper
    -0.67
     Sampson
    -0.66
    verwijspagina
    -0.66
    Externí
    -0.65
     Privacidade
    -0.63
    PostInfinity
    -0.62
    \{\\
    -0.58
     Andersson
    -0.58
     виправивши
    -0.58
    POSITIVE LOGITS
     sh
    3.20
    sh
    3.06
     Sh
    3.03
    Sh
    2.97
    SH
    2.14
     SH
    2.13
     shunt
    1.77
     Shu
    1.44
    shm
    1.38
     Shanks
    1.38
    Activations Density 0.187%

    No Known Activations