© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 600
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a high degree or emphasis

    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
    ็จ
    -0.75
    ötzlich
    -0.73
    همچنین
    -0.73
    forRoot
    -0.71
    xically
    -0.69
     urgently
    -0.68
    FormTagHelper
    -0.67
     undersigned
    -0.66
    ynchronously
    -0.66
    tdessen
    -0.65
    POSITIVE LOGITS
     quite
    3.06
     pretty
    2.97
    quite
    2.84
     Quite
    2.73
    Quite
    2.72
    pretty
    2.69
     fairly
    2.63
    Pretty
    2.55
     Pretty
    2.42
     Fairly
    2.22
    Activations Density 0.585%

    No Known Activations