© 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. 6304
    Prev
    Next
    INDEX
    Explanations

    references to the practicality of a subject or proposal

    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
    oneofs
    -0.73
    quelize
    -0.68
    UnusedPrivate
    -0.63
     noDo
    -0.63
    ResponseWriter
    -0.59
    semitism
    -0.59
     disambiguazione
    -0.59
    thâu
    -0.59
     Autorisations
    -0.59
    ########.
    -0.59
    POSITIVE LOGITS
     practical
    3.09
     Practical
    2.97
    Practical
    2.92
    practical
    2.91
     PRACTICAL
    2.61
     praktische
    2.19
     practicality
    2.19
     práctico
    2.16
     praktischen
    1.91
     prácti
    1.89
    Activations Density 0.011%

    No Known Activations