© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 383
    Prev
    Next
    INDEX
    Explanations

    details related to time periods, particularly years and dates in the format of 4-digit years (e.g. 1998, 2005) or specific dates (e.g. May 5, 2005).

    oai_token-act-pair · claude-3-5-sonnet-20240620
    Triggered by @trainjumperx

    technical and scientific terminology, particularly related to technological systems and devices.

    oai_token-act-pair · claude-3-5-haiku-20241022
    Triggered by @trainjumperx

    technical descriptions or specifications in formal documents, especially focusing on numerical measurements and technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @trainjumperx

    details related to optical devices and imaging processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    SuspendLayout
    -0.42
    +#+#
    -0.41
    tidaknya
    -0.40
    AddTagHelper
    -0.38
     betweenstory
    -0.38
     newest
    -0.35
     nanti
    -0.35
    sfw
    -0.35
    läufe
    -0.35
     appunto
    -0.34
    POSITIVE LOGITS
     Normdatei
    0.76
    MigrationBuilder
    0.67
    hoeddwyd
    0.65
     informée
    0.62
    хьтан
    0.62
    BufferException
    0.59
    ViewFeatures
    0.59
    IUrlHelper
    0.59
     kasarigan
    0.58
     Савезне
    0.58
    Activations Density 28.999%

    No Known Activations