© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4353
    Prev
    Next
    INDEX
    Explanations

    direct quotes

    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
    يميديا
    -0.52
     heard
    -0.44
    ef
    -0.43
    نجليزية
    -0.42
    MENAFN
    -0.40
     contemplate
    -0.40
    pesar
    -0.40
     teve
    -0.39
     (
    -0.38
     teil
    -0.38
    POSITIVE LOGITS
     trying
    0.73
     propOrder
    0.70
     SwitchCompat
    0.69
    hyrchwyd
    0.67
    WriteTagHelper
    0.66
    DeleteBehavior
    0.65
    trying
    0.64
    fromnode
    0.63
     ErrIntOverflow
    0.63
    RegressionTest
    0.63
    Activations Density 0.001%

    No Known Activations