© 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. 0-CLT-HP
    7. 41207
    Prev
    Next
    INDEX
    Explanations

    known

    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
     tocó
    -0.51
     cerrados
    -0.49
     CORS
    -0.48
     oraciones
    -0.46
     fin
    -0.45
    äum
    -0.45
     autorisés
    -0.45
     sanitaire
    -0.45
    achat
    -0.44
     uſed
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.75
    DockStyle
    0.61
    ChildScrollView
    0.58
    principalTable
    0.58
    ValueStyle
    0.57
    uxxxx
    0.57
    Démographie
    0.56
     noDo
    0.56
    crombie
    0.55
    躇
    0.55
    Activations Density 0.307%

    No Known Activations