© 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. 11594
    Prev
    Next
    INDEX
    Explanations

    patterns related to high-frequency oscillations or wave activity

    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
     paragraph
    -1.16
     Paragraph
    -1.04
     paragraphs
    -0.93
    paragraph
    -0.93
    Paragraph
    -0.88
    paragraphs
    -0.69
    KommentareTeilen
    -0.60
     paragraphe
    -0.58
     sexuales
    -0.53
     dedans
    -0.53
    POSITIVE LOGITS
    uparrow
    3.28
    ↑
    0.93
    ⓧ
    0.84
    OGND
    0.76
    lceil
    0.70
    Espèce
    0.62
    
    0.60
    AndEndTag
    0.59
    ↑↑
    0.58
    rags
    0.56
    Activations Density 0.002%

    No Known Activations