© 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. 14265
    Prev
    Next
    INDEX
    Explanations

    boot

    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
     ब्रेकडाउन
    -0.60
    发表于
    -0.59
    rungsseite
    -0.58
     BoxFit
    -0.57
    NewUrlParser
    -0.57
    :✨
    -0.56
     juges
    -0.54
    +#+#
    -0.54
     trajets
    -0.54
    utives
    -0.54
    POSITIVE LOGITS
     itſelf
    0.72
     myſelf
    0.65
     himſelf
    0.65
     themſelves
    0.60
     juſt
    0.59
     Houſe
    0.58
    yntaxException
    0.58
     raiſ
    0.57
     AGB
    0.57
     uſ
    0.56
    Activations Density 0.012%

    No Known Activations