© 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. 38628
    Prev
    Next
    INDEX
    Explanations

    thanks

    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
    ConstraintMaker
    -0.98
     }{@
    -0.95
     resourceCulture
    -0.91
     betweenstory
    -0.88
    NUMX
    -0.88
    gnition
    -0.87
    "]();
    -0.87
    LookAnd
    -0.84
    CloseOperation
    -0.84
    kloped
    -0.83
    POSITIVE LOGITS
    ,
    1.20
     you
    1.05
     we
    0.81
     there
    0.81
     it
    0.76
     the
    0.73
     they
    0.73
     one
    0.72
     a
    0.69
    !
    0.65
    Activations Density 0.058%

    No Known Activations