© 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. 2-RES-MATRYOSHKA-DC
    7. 6936
    Prev
    Next
    INDEX
    Explanations

    references to specific ways or styles of doing something

    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
     initComponents
    -0.79
    WindowConstants
    -0.69
    tagHelperRunner
    -0.63
     Hughes
    -0.62
    Ouch
    -0.61
    InjectAttribute
    -0.60
     صوتيه
    -0.60
     Tuf
    -0.59
    TagHelper
    -0.58
    tlere
    -0.58
    POSITIVE LOGITS
     manner
    2.97
    manner
    2.56
     Manner
    2.45
     manners
    1.95
     Manners
    1.24
     manor
    1.09
     fashion
    1.08
     demeanor
    0.80
     wijze
    0.77
    fashion
    0.76
    Activations Density 0.010%

    No Known Activations