© 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. 5301
    Prev
    Next
    INDEX
    Explanations

    prevention and damage reduction

    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
     Any
    -0.70
    Any
    -0.59
     例
    -0.51
    alka
    -0.45
    спі
    -0.44
    Differ
    -0.43
     Anything
    -0.43
    Specific
    -0.43
    Particular
    -0.43
     Specific
    -0.42
    POSITIVE LOGITS
     most
    0.74
     <=",
    0.67
    脚注の使い方
    0.67
     alot
    0.66
     many
    0.66
     beaucoup
    0.65
     much
    0.65
     ExecuteAsync
    0.65
    sizeCache
    0.63
     some
    0.62
    Activations Density 0.001%

    No Known Activations