© 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. 4-CLT-HP
    7. 2108
    Prev
    Next
    INDEX
    Explanations

    code and punctuation fragments

    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
    NameInMap
    -0.65
    flink
    -0.59
    onViewCreated
    -0.59
     jScrollPane
    -0.59
    Geplaatst
    -0.54
    encji
    -0.53
    inerja
    -0.52
     feedback
    -0.52
     olympique
    -0.51
     Hampden
    -0.51
    POSITIVE LOGITS
     estekak
    0.53
    Parcelize
    0.52
     muualla
    0.52
    Enllaces
    0.52
    principalColumn
    0.47
    FormTagHelper
    0.47
    ViewImports
    0.46
    amable
    0.46
    RunAsync
    0.44
    帖最后由
    0.44
    Activations Density 0.001%

    No Known Activations