© 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. 0-CLT-HP
    7. 90455
    Prev
    Next
    INDEX
    Explanations

    helpfulness

    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
     useful
    -1.46
    useful
    -1.40
     helpful
    -1.37
    helpful
    -1.34
     beneficial
    -1.21
     útil
    -1.13
     Useful
    -1.06
    Useful
    -1.05
     útiles
    -1.00
     valuable
    -0.98
    POSITIVE LOGITS
    ness
    0.64
     clinical
    0.56
     action
    0.54
     way
    0.50
     expression
    0.50
     manner
    0.49
     civilian
    0.48
     for
    0.48
     ones
    0.48
     to
    0.47
    Activations Density 0.108%

    No Known Activations