© 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. 4-CLT-HP
    7. 1150
    Prev
    Next
    INDEX
    Explanations

    a

    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
    KommentareTeilen
    -0.81
     @"/
    -0.60
    }\]
    -0.54
     MainAxisSize
    -0.53
    '}),
    -0.50
    pout
    -0.50
    WHEREAS
    -0.49
    FirstResponder
    -0.48
     lemp
    -0.46
    ={({
    -0.46
    POSITIVE LOGITS
     brancas
    0.64
     détru
    0.60
     pinulongan
    0.59
     näin
    0.59
     néglig
    0.59
    complexContent
    0.58
    HasForeignKey
    0.57
     définiti
    0.57
    TestBed
    0.56
     chré
    0.56
    Activations Density 0.004%

    No Known Activations