© 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. 73244
    Prev
    Next
    INDEX
    Explanations

    there

    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
     pinulongan
    -0.65
     ſtate
    -0.61
     föruts
    -0.60
     fourrure
    -0.58
    omiast
    -0.57
     varandra
    -0.56
     edelstahl
    -0.56
     pétrole
    -0.56
     CreateTagHelper
    -0.54
     cauſe
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    Tē
    0.55
     were
    0.55
    KURZBESCHREIBUNG
    0.53
    IUrlHelper
    0.52
     around
    0.51
    Ligações
    0.51
    []>(
    0.50
    Enlaces
    0.50
     than
    0.50
    Activations Density 0.001%

    No Known Activations