© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94473
    Prev
    Next
    INDEX
    Explanations

    refining or minimizing

    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
     revision
    -0.82
     Revision
    -0.78
     refined
    -0.75
     revisions
    -0.73
    revision
    -0.67
     revised
    -0.67
     refinement
    -0.66
     revise
    -0.66
     Revisions
    -0.66
     CreateTagHelper
    -0.64
    POSITIVE LOGITS
     snippetHide
    0.55
     TEMPLATE
    0.52
     bang
    0.51
    Παραπομπές
    0.50
     CURIAM
    0.49
     NgModule
    0.47
     createSlice
    0.47
    ọn
    0.46
    สัม
    0.46
    Ошибка
    0.46
    Activations Density 0.481%

    No Known Activations