© 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. 6669
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative judgment or criticism

    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
     unclear
    -0.52
    不一定
    -0.50
     inability
    -0.47
     olympique
    -0.47
     unable
    -0.46
     osa
    -0.45
    不太
    -0.44
     uncertain
    -0.44
     Stout
    -0.44
    ekt
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.81
     Wicidata
    0.81
     endwhile
    0.80
    UrlResolution
    0.78
    testify
    0.77
    AnimationsModule
    0.76
    
    0.75
    ніципа
    0.73
    RenderAtEndOf
    0.71
    Datuak
    0.71
    Activations Density 0.338%

    No Known Activations