© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11358
    Prev
    Next
    INDEX
    Explanations

    numerical sequences, measurements, or labels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.69
    gnügen
    -0.56
     BTU
    -0.56
    giène
    -0.55
    dialement
    -0.52
     Peoria
    -0.52
     Tapia
    -0.51
    AnchorStyles
    -0.51
    guarantee
    -0.50
     Koto
    -0.48
    POSITIVE LOGITS
     Hur
    3.73
    Hur
    3.59
     hur
    3.06
    hur
    2.77
     HUR
    2.45
    HUR
    2.25
     Hür
    1.43
     hurdle
    1.27
     Hurst
    1.16
     Hurricanes
    1.09
    Activations Density 0.001%

    No Known Activations