© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    references to authoritative sources or repeated mentions of an "informant" figure

    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
     IEnumerator
    -0.85
     propOrder
    -0.72
    ftagPool
    -0.68
    "}")
    -0.66
    .*")]
    -0.66
    adaptiveStyles
    -0.66
    izr
    -0.66
    braio
    -0.65
    jsxFileName
    -0.65
    subpackage
    -0.65
    POSITIVE LOGITS
     Caldwell
    0.77
     thence
    0.77
    asymp
    0.75
     hereafter
    0.75
    truct
    0.71
     overturned
    0.70
    isome
    0.70
     overturn
    0.70
    gone
    0.68
     podium
    0.68
    Activations Density 0.056%

    No Known Activations