© 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. 5-CLT-HP
    7. 4924
    Prev
    Next
    INDEX
    Explanations

    past, hypothetical events

    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
    
    -0.66
     gotten
    -0.50
    getDoctrine
    -0.49
    CodeAnalysis
    -0.48
     useHistory
    -0.48
     TestCase
    -0.48
    bürger
    -0.45
     ninh
    -0.45
     információk
    -0.44
    +};
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.80
    hyrchwyd
    0.65
     виправивши
    0.64
    ValueStyle
    0.64
     समीक्षक
    0.63
    DoubleQuotes
    0.60
     الحره
    0.60
     يتيمه
    0.58
    மை
    0.56
    ftagPool
    0.56
    Activations Density 0.001%

    No Known Activations