© 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. 0-CLT-HP
    7. 95159
    Prev
    Next
    INDEX
    Explanations

    cleaning, problems, solutions, reporting

    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
     Systems
    -0.42
     stain
    -0.42
    dinner
    -0.40
     hvis
    -0.39
     (
    -0.39
     All
    -0.38
     "
    -0.38
    removeClass
    -0.38
     que
    -0.37
    ystems
    -0.37
    POSITIVE LOGITS
    theless
    1.18
     estekak
    1.01
    adays
    0.95
    Autoritní
    0.94
    ization
    0.93
    RenderAtEndOf
    0.92
     дописавши
    0.91
    expandindo
    0.91
    lihood
    0.87
    ViewFeatures
    0.86
    Activations Density 0.274%

    No Known Activations