© 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. 1-CLT-HP
    7. 9293
    Prev
    Next
    INDEX
    Explanations

    margin

    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
    shtml
    -0.52
     esta
    -0.45
    ci
    -0.45
     page
    -0.44
    ly
    -0.44
     T
    -0.42
     Me
    -0.41
    ляр
    -0.40
    <eos>
    -0.40
     Bin
    -0.40
    POSITIVE LOGITS
    InputBorder
    0.96
    WebVitals
    0.94
    CloseOperation
    0.94
     BoxFit
    0.92
     AttributeSet
    0.91
    ContentAsync
    0.84
    migrationBuilder
    0.84
    Tikang
    0.83
     pinulongan
    0.83
     FormControl
    0.83
    Activations Density 0.032%

    No Known Activations