© 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. 94858
    Prev
    Next
    INDEX
    Explanations

    home

    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
     home
    -0.93
     HOME
    -0.80
     Home
    -0.75
     hjem
    -0.72
     homes
    -0.68
    home
    -0.64
    Home
    -0.62
     HOMES
    -0.62
    HOME
    -0.60
    bootstrapcdn
    -0.57
    POSITIVE LOGITS
    verwijspagina
    0.66
     theater
    0.65
     bezeichneter
    0.62
    ſelf
    0.60
     theatre
    0.60
    parsedMessage
    0.60
     Shakspeare
    0.60
    body
    0.59
     cooked
    0.59
    RenderAtEndOf
    0.58
    Activations Density 0.050%

    No Known Activations