© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95434
    Prev
    Next
    INDEX
    Explanations

    Scientific journals & companies

    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
    RenderAtEndOf
    -0.84
     المعيارى
    -0.82
     BoxFit
    -0.78
     plc
    -0.77
    endphp
    -0.75
    AndEndTag
    -0.75
    ChildScrollView
    -0.75
     通販
    -0.73
    RectangleBorder
    -0.73
    InputTagHelper
    -0.73
    POSITIVE LOGITS
    ize
    0.58
    ements
    0.56
    ise
    0.51
    izing
    0.51
    idel
    0.49
    ite
    0.49
    ement
    0.49
    iteľ
    0.46
     igenom
    0.45
    able
    0.44
    Activations Density 1.441%

    No Known Activations