© 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. 93934
    Prev
    Next
    INDEX
    Explanations

    opinions or choices

    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
    Ideas
    -0.84
     ideas
    -0.75
     Paglinawan
    -0.75
    BeginContext
    -0.73
    ideas
    -0.72
     decisions
    -0.69
     priorities
    -0.69
     preferences
    -0.68
    脚注の使い方
    -0.68
    })`
    -0.66
    POSITIVE LOGITS
     about
    0.89
     and
    0.56
    about
    0.56
    ysz
    0.52
     About
    0.50
     expressed
    0.50
     relev
    0.50
    Hardness
    0.50
     for
    0.50
     ABOUT
    0.50
    Activations Density 0.102%

    No Known Activations