© 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. 5325
    Prev
    Next
    INDEX
    Explanations

    varied topics

    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
    MemoryWarning
    -0.88
     AssemblyCulture
    -0.85
     CreateTagHelper
    -0.83
    DeleteBehavior
    -0.82
     يتيمه
    -0.81
    findpost
    -0.75
    IsMutable
    -0.75
    PerformLayout
    -0.74
    RectangleBorder
    -0.74
    VersionUID
    -0.73
    POSITIVE LOGITS
     checked
    0.72
     examined
    0.71
     investigated
    0.62
     measured
    0.62
     tested
    0.61
     found
    0.59
     explored
    0.53
    checked
    0.52
     studied
    0.52
     done
    0.51
    Activations Density 0.013%

    No Known Activations