© 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. 1-CLT-HP
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    Code snippets and abbreviations

    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
    Comté
    -0.62
    a
    -0.56
     Meter
    -0.56
     meter
    -0.55
    ecake
    -0.54
     الحره
    -0.52
    Meter
    -0.52
    e
    -0.50
    Suara
    -0.50
    ChildScrollView
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    лтемелер
    0.66
    StoryboardSegue
    0.63
    AccessorTable
    0.62
    GenerationType
    0.60
    offsetof
    0.57
    badlogic
    0.56
    Geplaatst
    0.55
    ellido
    0.54
    انيف
    0.54
    Activations Density 0.833%

    No Known Activations