© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41277
    Prev
    Next
    INDEX
    Explanations

    {

    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
    cense
    -1.02
    astify
    -0.78
     obicei
    -0.78
     Italijanski
    -0.77
    Brainz
    -0.76
    IVEREF
    -0.75
    limus
    -0.71
     jadx
    -0.70
    StoryboardSegue
    -0.69
    shadowOpacity
    -0.69
    POSITIVE LOGITS
     all
    0.50
     pa
    0.48
     All
    0.45
    umenta
    0.44
    ↵↵
    0.44
    parametrize
    0.41
     
    0.39
     Let
    0.39
    iega
    0.38
     Wie
    0.38
    Activations Density 0.057%

    No Known Activations