© 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. 0-RES-MATRYOSHKA-DC
    7. 14274
    Prev
    Next
    INDEX
    Explanations

    references to the word "reveal," indicating its focus is on detecting instances where something is uncovered or disclosed

    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
     дописавши
    -0.85
     незавершена
    -0.70
    IndentedString
    -0.69
    NameInMap
    -0.68
     discovered
    -0.67
     EconPapers
    -0.66
     Discovered
    -0.66
    RenderAtEndOf
    -0.66
     Announced
    -0.64
     announced
    -0.63
    POSITIVE LOGITS
     reveal
    1.59
    reveal
    1.53
     Reveal
    1.39
    Reveal
    1.31
     revealing
    1.13
     reveals
    0.91
    reve
    0.76
     revelar
    0.68
     Reveals
    0.67
     révé
    0.65
    Activations Density 0.004%

    No Known Activations