© 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. 20-CLT-HP
    7. 73695
    Prev
    Next
    INDEX
    Explanations

    not

    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
     GenerationType
    -0.76
    Getting
    -0.69
     Getting
    -0.68
    Adding
    -0.64
     Obtaining
    -0.63
    having
    -0.63
    getting
    -0.62
     EconPapers
    -0.62
     GETTING
    -0.62
     saites
    -0.60
    POSITIVE LOGITS
     not
    1.54
    not
    1.05
     NOT
    0.89
    Not
    0.77
     Not
    0.74
     bukan
    0.68
    NOT
    0.67
     mitte
    0.61
     ikke
    0.60
    noty
    0.60
    Activations Density 0.001%

    No Known Activations