© 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. 5-CLT-HP
    7. 2553
    Prev
    Next
    INDEX
    Explanations

    General English sentences

    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
     somewhat
    -0.64
     pretty
    -0.53
    Somewhat
    -0.53
     nice
    -0.52
    somewhat
    -0.49
     Somewhat
    -0.47
     sort
    -0.46
     way
    -0.45
    比较好
    -0.44
     beetje
    -0.42
    POSITIVE LOGITS
    IndentedString
    0.93
    LookAnd
    0.90
    Personendaten
    0.86
    GraphicsUnit
    0.84
     Roskov
    0.77
    AccessorTable
    0.77
    ///</
    0.77
     NSCoder
    0.77
     CreateTagHelper
    0.76
    parsedMessage
    0.76
    Activations Density 0.005%

    No Known Activations