© 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. 0-CLT-HP
    7. 94940
    Prev
    Next
    INDEX
    Explanations

    mutual

    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
    ishment
    -1.42
    MLLoader
    -0.95
    onViewCreated
    -0.87
     from
    -0.85
    ⓧ
    -0.83
    Chham
    -0.81
    DockStyle
    -0.79
    IUrlHelper
    -0.79
     propOrder
    -0.77
     Chwiliwch
    -0.76
    POSITIVE LOGITS
     Tre
    0.49
     Gra
    0.47
     the
    0.47
    ordin
    0.47
     Ober
    0.47
     a
    0.46
    lue
    0.46
     Associated
    0.46
     Dou
    0.45
     Shared
    0.45
    Activations Density 1.608%

    No Known Activations