© 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. 1-CLT-HP
    7. 9992
    Prev
    Next
    INDEX
    Explanations

    radionuc

    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
    e
    -0.59
    ChildIndex
    -0.56
     floating
    -0.52
     Scully
    -0.47
    i
    -0.47
     Floating
    -0.47
     pepper
    -0.47
     client
    -0.46
    榴
    -0.46
     pin
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.62
    XmlAccessType
    0.58
     GenerationType
    0.56
     referrerpolicy
    0.55
     vectoriales
    0.53
    =$?
    0.52
     оригіналу
    0.51
    таратура
    0.51
    BibitemShut
    0.51
    %}
    0.50
    Activations Density 0.027%

    No Known Activations