© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 586
    Prev
    Next
    INDEX
    Explanations

    sign

    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
     sign
    -0.71
     signs
    -0.62
     Sign
    -0.58
     signe
    -0.57
     Signs
    -0.51
     SIGNS
    -0.50
     signes
    -0.47
     signo
    -0.43
     SIGN
    -0.43
    sign
    -0.42
    POSITIVE LOGITS
    msgTypes
    0.67
     resourceCulture
    0.66
    تقاوى
    0.65
    endpush
    0.65
     AssemblyTitle
    0.64
     ويكيپيديا
    0.62
     يتيمه
    0.62
    IndentedString
    0.61
    himu
    0.61
    portar
    0.60
    Activations Density 0.003%

    No Known Activations