© 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. 1-RES-MATRYOSHKA-DC
    7. 976
    Prev
    Next
    INDEX
    Explanations

    the second derivative of a mathematical function

    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
     Metz
    -0.56
    Atlan
    -0.54
    ExecuteReader
    -0.54
    rition
    -0.53
    bitos
    -0.50
    writeFieldEnd
    -0.49
    UNI
    -0.48
     сожалению
    -0.48
     Atlan
    -0.47
     RECON
    -0.47
    POSITIVE LOGITS
     derivative
    3.92
     derivatives
    3.59
     Derivative
    3.45
    derivative
    3.38
     Derivatives
    3.17
    deriv
    3.09
    Deriv
    2.95
    Derivative
    2.95
     deriv
    2.94
     Deriv
    2.64
    Activations Density 0.555%

    No Known Activations