© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45982
    Prev
    Next
    INDEX
    Explanations

    turn

    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
     CreateTagHelper
    -0.85
    tagHelperRunner
    -0.75
     springfox
    -0.69
     onAnimation
    -0.68
     unknownFields
    -0.67
     تضيفلها
    -0.66
    principalTable
    -0.61
     onCancelled
    -0.60
    AndEndTag
    -0.59
    ities
    -0.58
    POSITIVE LOGITS
    ustering
    0.48
    Legit
    0.46
    athione
    0.46
    olverine
    0.45
    achusetts
    0.45
     Generations
    0.44
    Wyd
    0.44
    oczes
    0.44
    ientôt
    0.44
    hamilan
    0.43
    Activations Density 0.010%

    No Known Activations