© 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. 5879
    Prev
    Next
    INDEX
    Explanations

    descriptive 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
     שוליים
    -0.68
    LogFactory
    -0.59
    }>;
    -0.58
     ils
    -0.51
    operatively
    -0.49
    Merhaba
    -0.47
    wnia
    -0.45
     Investigations
    -0.45
    InSection
    -0.45
    suchen
    -0.45
    POSITIVE LOGITS
    keyColumn
    0.67
    ChildScrollView
    0.62
    NOPQRST
    0.60
     InputDecoration
    0.58
     getRule
    0.57
     Baal
    0.57
    RegressionTest
    0.57
    ConstraintMaker
    0.56
    luia
    0.55
     Amman
    0.55
    Activations Density 0.001%

    No Known Activations