© 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. 91338
    Prev
    Next
    INDEX
    Explanations

    Instructions

    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
    of
    -0.49
     carrier
    -0.45
     provisional
    -0.43
     standing
    -0.42
     bint
    -0.40
     this
    -0.40
     tentative
    -0.40
     of
    -0.39
    OF
    -0.39
     unofficial
    -0.39
    POSITIVE LOGITS
     Roskov
    1.02
     kaarangay
    0.97
     AssemblyProduct
    0.88
     propOrder
    0.82
     estekak
    0.78
     initComponents
    0.76
     AssemblyTitle
    0.76
    enumi
    0.75
    parsedMessage
    0.73
    +#+#
    0.73
    Activations Density 0.004%

    No Known Activations