© 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. 1-CLT-HP
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    financial reporting/news updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.87
    principalTable
    -0.70
    Билгалдахарш
    -0.69
    Expedia
    -0.66
     protoimpl
    -0.66
    InputBorder
    -0.66
     MainAxisSize
    -0.65
     estekak
    -0.64
    Зноскі
    -0.60
    expandindo
    -0.60
    POSITIVE LOGITS
     of
    0.59
    rawDesc
    0.49
    ofthe
    0.48
     marcos
    0.44
    ists
    0.43
    iat
    0.42
    пора
    0.42
     sources
    0.42
     Folge
    0.42
    idavit
    0.42
    Activations Density 0.028%

    No Known Activations