© 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. 5-CLT-HP
    7. 92657
    Prev
    Next
    INDEX
    Explanations

    Defining words

    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
    SpringBoot
    -0.45
     NgModule
    -0.43
    nodoc
    -0.43
    ApplicationTests
    -0.42
    endforeach
    -0.42
    UBLIC
    -0.41
    Còn
    -0.40
    trons
    -0.39
    MenuInflater
    -0.39
    ungan
    -0.39
    POSITIVE LOGITS
    kháu
    0.76
    SourceChecksum
    0.75
     typelib
    0.67
    verifyException
    0.63
    ValueStyle
    0.63
     الرياضيه
    0.60
     ostavi
    0.59
    tamol
    0.58
    windowFixed
    0.58
    StructEnd
    0.57
    Activations Density 0.002%

    No Known Activations