© 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. 77188
    Prev
    Next
    INDEX
    Explanations

    Technical snippets

    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
    bari
    -0.63
     nationaux
    -0.57
    writeFieldEnd
    -0.55
    StructEnd
    -0.51
    قایناقلار
    -0.50
     sauvages
    -0.49
    RegressionTest
    -0.49
    SharedCtor
    -0.49
     naturelles
    -0.48
     frappé
    -0.47
    POSITIVE LOGITS
    Datuak
    0.71
    ValueStyle
    0.69
    Geplaatst
    0.66
    limus
    0.56
    WillAppear
    0.53
    ArrowToggle
    0.53
    setAccessible
    0.51
    Rhestr
    0.50
     allAfrica
    0.49
    DllImport
    0.48
    Activations Density 0.003%

    No Known Activations