© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1377
    Prev
    Next
    INDEX
    Explanations

    legal terms, place names, and names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mandy
    -0.87
    Juli
    -0.79
    Mandy
    -0.79
     Remastered
    -0.78
     Roch
    -0.75
     Woolf
    -0.75
     Rockford
    -0.73
     kuy
    -0.73
     Juli
    -0.72
     Cuen
    -0.72
    POSITIVE LOGITS
     Dent
    0.98
     كومونز
    0.96
    Horses
    0.91
    Dent
    0.89
     Salom
    0.88
    AndEndTag
    0.88
     betre
    0.84
     Washington
    0.82
    Columb
    0.82
     DC
    0.79
    Activations Density 4.713%

    No Known Activations