© 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. 93869
    Prev
    Next
    INDEX
    Explanations

    honesty/clarity marker

    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
     convertView
    -0.57
     ujednoznacz
    -0.55
    e
    -0.55
     Allegro
    -0.51
    pence
    -0.51
    glass
    -0.49
    worthiness
    -0.49
    fares
    -0.48
    ChildScrollView
    -0.47
    €/
    -0.47
    POSITIVE LOGITS
    jspx
    0.66
    IMPORTED
    0.65
     CreateTagHelper
    0.64
    principalColumn
    0.62
    webElementXpaths
    0.61
     nahilalakip
    0.60
    PerformLayout
    0.58
    abestanden
    0.57
     Recognized
    0.55
    usermodel
    0.54
    Activations Density 0.101%

    No Known Activations