© 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. 0-CLT-HP
    7. 94933
    Prev
    Next
    INDEX
    Explanations

    Parks/Cut-outs

    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
    outs
    -1.31
    ash
    -0.92
    ASH
    -0.65
    Outs
    -0.64
    ed
    -0.61
     coach
    -0.61
     hang
    -0.60
     Parks
    -0.59
    ly
    -0.58
    est
    -0.57
    POSITIVE LOGITS
     EconPapers
    1.09
    DockStyle
    1.09
    ScopeManager
    1.05
     defaultstate
    1.04
    MigrationBuilder
    1.04
    AddTagHelper
    1.01
     snippetHide
    1.01
    DoubleQuotes
    1.00
    ContentAsync
    1.00
    \{\\
    0.99
    Activations Density 0.073%

    No Known Activations