© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3502
    Prev
    Next
    INDEX
    Explanations

    in

    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
    endphp
    -0.75
    NewUrlParser
    -0.73
     initComponents
    -0.71
    脚注の使い方
    -0.69
    /**
    -0.65
    adaptiveStyles
    -0.65
    AndEndTag
    -0.63
     GenerationType
    -0.62
     <<<<<<<<<<<<<<
    -0.59
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     mówią
    0.54
     analysts
    0.50
    @#
    0.50
     lī
    0.49
     culturelle
    0.48
    mans
    0.47
     régionale
    0.47
    ändler
    0.47
     tavola
    0.47
     venner
    0.47
    Activations Density 0.001%

    No Known Activations