© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91599
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     are
    -0.58
    NORE
    -0.50
    covite
    -0.50
     has
    -0.48
    ึ้น
    -0.47
     have
    -0.47
    imente
    -0.46
     mục
    -0.45
    ويد
    -0.45
    nox
    -0.45
    POSITIVE LOGITS
    hyrchwyd
    0.80
    Diweddarwch
    0.68
    PerformLayout
    0.64
     onAnimation
    0.61
    StoryboardSegue
    0.61
    migrationBuilder
    0.57
    StoreMessageInfo
    0.57
     invokingState
    0.55
    ">*</
    0.55
     niyang
    0.54
    Activations Density 0.002%

    No Known Activations