© 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. 20-CLT-HP
    7. 72156
    Prev
    Next
    INDEX
    Explanations

    Code and random words

    np_max-act-logits · 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
    uxxxx
    -0.50
    GRANTED
    -0.50
    =$?
    -0.45
     AssemblyCulture
    -0.44
    енча
    -0.43
    yor
    -0.43
    ondata
    -0.42
    ItemBackground
    -0.42
    ndata
    -0.42
     contextLoads
    -0.42
    POSITIVE LOGITS
    XPATH
    0.58
    RenderAtEndOf
    0.58
    ">//
    0.57
    ViewChild
    0.57
     Tour
    0.53
    InjectAttribute
    0.52
    ंदीखरीदारी
    0.52
     Fourth
    0.52
    Tour
    0.52
    Fourth
    0.51
    Activations Density 0.000%

    No Known Activations