© 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. 6797
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consulted" or "consulting."

    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
     незавершена
    -0.73
    клопе
    -0.70
    TypedDataSet
    -0.68
     organisers
    -0.62
    InitVars
    -0.62
    Билгалдахарш
    -0.61
    OGND
    -0.60
     itinéraires
    -0.60
     Tapa
    -0.59
     bai
    -0.59
    POSITIVE LOGITS
     consult
    3.19
     consulting
    3.14
     CONSULT
    3.08
     consultation
    2.94
    consult
    2.92
    Consult
    2.92
     Consult
    2.91
     consulted
    2.84
    CONSULT
    2.70
    Consulting
    2.67
    Activations Density 0.008%

    No Known Activations