© 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. 3-RES-MATRYOSHKA-DC
    7. 1350
    Prev
    Next
    INDEX
    Explanations

    mentions of measuring something, along with qualities and roles related to that measurement.

    oai_token-act-pair · gemini-2.0-flash
    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
    #
    -0.76
    +#+#
    -0.71
    foria
    -0.68
     textStatus
    -0.68
    ValueGeneration
    -0.66
    [^
    -0.65
    esgue
    -0.65
    wpdb
    -0.64
    ContentLoaded
    -0.63
     استنادى
    -0.63
    POSITIVE LOGITS
     of
    0.96
     possibilité
    0.70
     Fähigkeit
    0.65
     capables
    0.65
     hoeveel
    0.64
    newArrayList
    0.64
     wijze
    0.62
     posibilidad
    0.61
    OfType
    0.61
    copies
    0.59
    Activations Density 2.671%

    No Known Activations