© 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. 2-RES-MATRYOSHKA-DC
    7. 5643
    Prev
    Next
    INDEX
    Explanations

    comparisons of two things indicating contrast

    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
    ſelf
    -0.65
    katapos
    -0.65
    mtable
    -0.63
    ſelves
    -0.60
    ungkinkan
    -0.60
     ſeveral
    -0.60
     myſelf
    -0.59
    ništvo
    -0.59
     reaſon
    -0.57
     Jefus
    -0.56
    POSITIVE LOGITS
     whereas
    2.75
    whereas
    2.63
    Whereas
    2.47
     Whereas
    2.45
     sedangkan
    1.44
     WHEREAS
    1.33
    WHEREAS
    1.00
     Sedangkan
    0.98
     tandis
    0.90
    unlike
    0.88
    Activations Density 0.007%

    No Known Activations