© 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. 5046
    Prev
    Next
    INDEX
    Explanations

    statements expressing a high level of expectation or certainty

    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
     expected
    -0.89
     desired
    -0.85
    expected
    -0.78
     projected
    -0.78
     Expected
    -0.76
    desired
    -0.76
    Expected
    -0.73
     planned
    -0.71
     intended
    -0.68
     proposed
    -0.67
    POSITIVE LOGITS
    expect
    2.11
     Expect
    1.69
     expect
    1.63
    Expect
    1.60
    EXPECT
    1.44
     expectancy
    1.44
     expecting
    1.41
     expectation
    1.31
     Expectation
    1.26
    expectation
    1.10
    Activations Density 0.017%

    No Known Activations