© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97446
    Prev
    Next
    INDEX
    Explanations

    legal/threatening text

    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
     Deny
    -0.63
    ByUserId
    -0.60
    الإنجليزية
    -0.60
     AssemblyCompany
    -0.59
     friendship
    -0.57
    <bos>
    -0.57
     shadowed
    -0.57
     &___
    -0.57
    )];
    -0.57
    savings
    -0.57
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    arschijnlijk
    0.53
    ódó
    0.51
     rayures
    0.50
    keyframes
    0.46
     GoogleFonts
    0.46
     vetro
    0.46
    TagHelper
    0.43
    Zeneca
    0.42
    ьаж
    0.42
    Activations Density 0.000%

    No Known Activations