© 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. 6-RES-MATRYOSHKA-DC
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    a mix of words relating to computer code, song artists and chemistry

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     doInBackground
    -0.86
     Humphries
    -0.84
    PageContext
    -0.83
     Pute
    -0.81
    ed
    -0.79
     Pompey
    -0.79
    出版年
    -0.77
     StringTokenizer
    -0.77
     Dempsey
    -0.76
    martre
    -0.74
    POSITIVE LOGITS
    jil
    0.96
     Jol
    0.94
     SIL
    0.93
     Lel
    0.93
    zol
    0.90
     JL
    0.90
    hiel
    0.90
    JL
    0.89
    JAL
    0.89
     Zil
    0.89
    Activations Density 3.694%

    No Known Activations