© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    references to the second derivative of a function or expression

    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
    writeFieldEnd
    -0.78
    amaño
    -0.75
    Brainz
    -0.73
    chism
    -0.73
     noDo
    -0.73
    AccessorTable
    -0.72
    SBATCH
    -0.72
    TypedDataSet
    -0.71
    Sucesor
    -0.69
     كومونز
    -0.68
    POSITIVE LOGITS
    rt
    2.05
    RT
    1.36
     rt
    1.34
     RT
    1.12
    Rt
    0.99
    rts
    0.90
    wrt
    0.83
    рт
    0.79
     Rt
    0.73
    irt
    0.70
    Activations Density 0.009%

    No Known Activations