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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97974
    Prev
    Next
    INDEX
    Explanations

    Doubling/multiplication

    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
     Aren
    -0.40
     rec
    -0.40
     Is
    -0.40
    they
    -0.39
     Isn
    -0.39
     minha
    -0.39
    Theres
    -0.38
     signal
    -0.38
     h
    -0.38
     pää
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.98
    AndEndTag
    0.95
     the
    0.94
    IsMutable
    0.87
    ConstraintMaker
    0.81
    TestingModule
    0.80
    NewUrlParser
    0.78
    +#+#
    0.75
    DockStyle
    0.75
    bitField
    0.75
    Activations Density 0.001%

    No Known Activations