© 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. 20-CLT-HP
    7. 75626
    Prev
    Next
    INDEX
    Explanations

    Names and titles

    np_max-act-logits · 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
    expandindo
    -0.77
    AndEndTag
    -0.65
     AssemblyCulture
    -0.63
    __":
    -0.60
     propOrder
    -0.59
    __':
    -0.58
     goog
    -0.58
    AsUp
    -0.57
     jsPsych
    -0.56
     mergeFrom
    -0.54
    POSITIVE LOGITS
    SizeMode
    0.62
    idać
    0.55
     referred
    0.53
    Edm
    0.52
     CreateTagHelper
    0.50
     abbra
    0.45
     bicchiere
    0.45
     vistos
    0.43
     couvrir
    0.42
    DJANGO
    0.42
    Activations Density 0.002%

    No Known Activations