© 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. 2-RES-MATRYOSHKA-DC
    7. 4613
    Prev
    Next
    INDEX
    Explanations

    expressions of existence or identification

    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
    MigrationBuilder
    -0.98
    Personensuche
    -0.93
    rungsseite
    -0.88
     estekak
    -0.86
    keyColumn
    -0.81
    expandindo
    -0.81
    parsedMessage
    -0.79
    OGND
    -0.79
    DBNull
    -0.77
    PerformLayout
    -0.76
    POSITIVE LOGITS
     include
    0.61
     mine
    0.47
    包括
    0.45
    \\
    0.45
     licenci
    0.45
     '
    0.42
     Include
    0.42
     appunto
    0.42
    mine
    0.41
    :
    0.40
    Activations Density 0.583%

    No Known Activations