© 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. 330
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss analysis, evaluation, or comparison in various contexts

    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
     betweenstory
    -0.83
    GTCX
    -0.70
    MessageOf
    -0.69
     kasarigan
    -0.68
    rungsseite
    -0.64
    RTLR
    -0.64
     protoimpl
    -0.62
    opsida
    -0.60
    RTEE
    -0.59
    SequentialGroup
    -0.58
    POSITIVE LOGITS
    ,
    0.40
     vigencia
    0.37
    During
    0.35
     posesión
    0.34
     hormigón
    0.33
     this
    0.33
     bambú
    0.32
    ...,
    0.32
     compacto
    0.32
    Concerning
    0.32
    Activations Density 5.432%

    No Known Activations