© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 30013
    Prev
    Next
    INDEX
    Explanations

    the word "diesel."

    oai_token-act-pair · gemini-2.0-flash
    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
     avoit
    -0.82
    orianCalendar
    -0.82
     @"/
    -0.77
     Beller
    -0.77
     Konami
    -0.77
     tenement
    -0.76
     numberWith
    -0.76
    eronau
    -0.76
    PerformLayout
    -0.75
    HCO
    -0.75
    POSITIVE LOGITS
     Diesel
    1.73
     diesel
    1.70
    Diesel
    1.67
    diesel
    1.60
     DIES
    1.16
    SourceChecksum
    1.02
     дизе
    0.96
     Dies
    0.79
    柴
    0.75
    Dies
    0.73
    Activations Density 0.001%

    No Known Activations