Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39511
    Prev
    Next
    INDEX
    Explanations

    research

    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
    bolistas
    -0.81
     NSCoder
    -0.80
    ✨:
    -0.75
    runApp
    -0.74
    DockStyle
    -0.71
    drawiam
    -0.69
    pozdrawiam
    -0.69
    ConstraintMaker
    -0.69
     Chwiliwch
    -0.68
    NOPQRST
    -0.68
    POSITIVE LOGITS
     study
    0.50
     Plan
    0.50
     Fond
    0.48
     Study
    0.45
     Finish
    0.44
    Plan
    0.43
     and
    0.43
    w
    0.42
     we
    0.42
    Study
    0.42
    Activations Density 0.046%

    No Known Activations