© 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. 92163
    Prev
    Next
    INDEX
    Explanations

    party

    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
    cythe
    -0.51
    thalten
    -0.51
     respect
    -0.51
    AndEndTag
    -0.49
     perfons
    -0.49
     kya
    -0.48
     AssemblyCompany
    -0.48
    foria
    -0.48
     Aren
    -0.47
     nothing
    -0.47
    POSITIVE LOGITS
     has
    0.93
     is
    0.81
     can
    0.78
     gets
    0.72
     sees
    0.72
     was
    0.72
     earns
    0.71
     succeeds
    0.70
     owns
    0.70
     receives
    0.70
    Activations Density 0.002%

    No Known Activations