© 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. 151
    Prev
    Next
    INDEX
    Explanations

    documentation/tutorials

    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
    -1.06
     CreateTagHelper
    -0.95
    LookAnd
    -0.93
    MigrationBuilder
    -0.92
     myſelf
    -0.90
     itſelf
    -0.88
     uſed
    -0.82
     himſelf
    -0.81
     незавершена
    -0.80
    RuleContext
    -0.80
    POSITIVE LOGITS
     products
    0.45
     fronte
    0.42
     reference
    0.42
    -
    0.41
     measuring
    0.40
    kning
    0.39
     en
    0.39
    REFERENCE
    0.39
     serving
    0.39
     building
    0.38
    Activations Density 0.028%

    No Known Activations