© 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. 1-CLT-HP
    7. 9425
    Prev
    Next
    INDEX
    Explanations

    variable

    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
     variable
    -1.21
     variables
    -1.08
    variable
    -0.99
    Variable
    -0.98
     Variable
    -0.95
     Variables
    -0.91
     VARIABLE
    -0.85
    变量
    -0.82
    variables
    -0.81
     variabel
    -0.76
    POSITIVE LOGITS
    ItemBackground
    0.61
     puissante
    0.59
    AndEndTag
    0.57
    PreferredItem
    0.53
     complètes
    0.52
     terdekat
    0.51
     vastaan
    0.50
    loroethane
    0.48
    IsContent
    0.48
    NewRow
    0.48
    Activations Density 0.130%

    No Known Activations