© 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. 2-RES-MATRYOSHKA-DC
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical durations or quantities

    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
     ordenador
    -0.43
    年
    -0.42
     έναν
    -0.41
    另
    -0.40
    campista
    -0.40
     kelas
    -0.40
    心
    -0.39
     risk
    -0.39
     rare
    -0.39
    ṣ
    -0.39
    POSITIVE LOGITS
    PerformLayout
    1.02
     myſelf
    0.99
    RenderAtEndOf
    0.99
    MigrationBuilder
    0.93
    ########.
    0.87
     itſelf
    0.85
     Majefty
    0.82
    InjectAttribute
    0.82
     Италијани
    0.79
    neſs
    0.79
    Activations Density 0.323%

    No Known Activations