© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15704
    Prev
    Next
    INDEX
    Explanations

    references to high-level intellectual abilities or capacities

    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
    ArgsConstructor
    -0.83
    IsContent
    -0.81
    djangoproject
    -0.79
    RTEE
    -0.75
    FormTagHelper
    -0.72
    adaptiveStyles
    -0.72
     estimés
    -0.71
    KommentareTeilen
    -0.71
    DebuggerNonUser
    -0.70
     nakalista
    -0.69
    POSITIVE LOGITS
     intellectual
    2.80
    intellectual
    2.45
     Intellectual
    2.39
    Intellectual
    2.27
     intellectually
    1.70
     intelectual
    1.66
     intellectuelle
    1.48
     intellectuals
    1.23
     geisti
    1.11
     intelek
    1.08
    Activations Density 0.003%

    No Known Activations