© 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. 92517
    Prev
    Next
    INDEX
    Explanations

    and

    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
    FE
    -0.48
     solito
    -0.47
     persino
    -0.46
     smells
    -0.46
    chlag
    -0.45
     weighs
    -0.44
     détail
    -0.43
     offers
    -0.43
     is
    -0.42
     revisa
    -0.42
    POSITIVE LOGITS
    DockStyle
    1.08
    IntoConstraints
    0.92
    PerformLayout
    0.83
    tvguidetime
    0.81
    tagHelperRunner
    0.79
    styleType
    0.78
     AssemblyCulture
    0.75
    principalColumn
    0.74
     pinulongan
    0.74
    InjectAttribute
    0.74
    Activations Density 0.002%

    No Known Activations