© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4790
    Prev
    Next
    INDEX
    Explanations

    words indicating an impact or influence

    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
     Influence
    -0.96
     influence
    -0.93
    ագրություններ
    -0.91
     kasarigan
    -0.88
    Influence
    -0.85
    influence
    -0.82
     INFLUENCE
    -0.82
    ValueStyle
    -0.74
    migrationBuilder
    -0.72
     Wray
    -0.69
    POSITIVE LOGITS
     affected
    2.27
     Affected
    2.17
     AFFECT
    2.16
    affected
    1.97
    affect
    1.92
    Affected
    1.89
     affect
    1.82
     Affect
    1.80
     affects
    1.74
     affecting
    1.71
    Activations Density 0.029%

    No Known Activations