© 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. 42250
    Prev
    Next
    INDEX
    Explanations

    linked

    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
    linked
    -1.77
     linked
    -1.70
    Linked
    -1.70
     Linked
    -1.62
    linking
    -1.45
    Linking
    -1.45
     linking
    -1.42
     Linking
    -1.40
    LINK
    -1.19
    Link
    -1.13
    POSITIVE LOGITS
    RemoveField
    0.75
    errHandler
    0.73
    findpost
    0.73
    SerializedSize
    0.69
    WindowConstants
    0.65
    WithIOException
    0.64
    CppMethod
    0.63
    HtmlAttribute
    0.63
    Portály
    0.61
     سكانية
    0.61
    Activations Density 0.281%

    No Known Activations