© 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. 5-CLT-HP
    7. 92667
    Prev
    Next
    INDEX
    Explanations

    Connecting words

    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
    قایناقلار
    -0.54
    appspot
    -0.51
    ועל
    -0.49
     getItemCount
    -0.49
     sidan
    -0.47
    odic
    -0.46
     कहते
    -0.46
    esgue
    -0.45
    sequelize
    -0.45
     slå
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.88
     when
    0.75
     beginning
    0.69
    when
    0.66
    XDECREF
    0.66
    until
    0.63
    before
    0.62
     UNTIL
    0.62
     until
    0.61
     архивлан
    0.61
    Activations Density 0.002%

    No Known Activations