© 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. 4-CLT-HP
    7. 1315
    Prev
    Next
    INDEX
    Explanations

    it

    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
     pleaſure
    -0.56
    ArrowToggle
    -0.54
     whoſe
    -0.51
     myſelf
    -0.48
     himſelf
    -0.48
     ſtill
    -0.47
    sda
    -0.46
     kjem
    -0.46
     Efq
    -0.45
    nocache
    -0.44
    POSITIVE LOGITS
     Works
    0.88
     WORKS
    0.72
     works
    0.69
     Means
    0.66
     Matters
    0.63
     all
    0.62
    Works
    0.61
    CodedInputStream
    0.61
     kasarigan
    0.60
     Happens
    0.60
    Activations Density 0.001%

    No Known Activations