© 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. 4-CLT-HP
    7. 691
    Prev
    Next
    INDEX
    Explanations

    take

    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
    herself
    -0.66
    /*!
    -0.56
    ']))
    -0.55
    himself
    -0.54
    /*!
    -0.52
     herself
    -0.52
     himself
    -0.52
    avadoc
    -0.51
    ži
    -0.49
     yourself
    -0.48
    POSITIVE LOGITS
     Мексичка
    0.74
    WithIOException
    0.70
    ArrowToggle
    0.68
     GenerationType
    0.66
    StoryboardSegue
    0.66
     ویکی‌پدیای
    0.65
     utafitiHapana
    0.64
     оригіналу
    0.62
    encodeWith
    0.62
    CodeAttribute
    0.61
    Activations Density 0.004%

    No Known Activations