© 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. 93773
    Prev
    Next
    INDEX
    Explanations

    outline

    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
     outline
    -2.16
     Outline
    -1.79
    outline
    -1.59
    Outline
    -1.58
     outlines
    -1.58
     OUTLINE
    -1.37
     outlining
    -1.17
     volume
    -1.16
     outlined
    -1.16
    volume
    -1.02
    POSITIVE LOGITS
    AtIndexPath
    0.57
     of
    0.54
    LabelTagHelper
    0.52
    PreferredItem
    0.51
    ting
    0.48
    InstanceState
    0.46
    AddTagHelper
    0.46
    CSC
    0.43
     متعلقه
    0.42
    DllImport
    0.41
    Activations Density 1.680%

    No Known Activations