© 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. 3-RES-MATRYOSHKA-DC
    7. 1880
    Prev
    Next
    INDEX
    Explanations

    uses of the words "be", "is", "are", "was", and "were" to describe the way things are or could be

    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
    ChildScrollView
    -0.67
    ValueStyle
    -0.56
    vgili
    -0.54
    hnia
    -0.53
    prefixer
    -0.52
     FishBase
    -0.49
    MigrationBuilder
    -0.49
    ArgsConstructor
    -0.48
    gbaar
    -0.48
     therefore
    -0.48
    POSITIVE LOGITS
    dafx
    0.71
    ########.
    0.68
    \{\\
    0.63
     Réponses
    0.63
    webElementXpaths
    0.58
    UnitTesting
    0.58
    QMetaType
    0.56
     errado
    0.54
     informée
    0.54
     kaynağından
    0.53
    Activations Density 3.697%

    No Known Activations