© 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. 3995
    Prev
    Next
    INDEX
    Explanations

    x

    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
    AutoresizingMask
    -0.70
    ngdoc
    -0.67
     MainAxisSize
    -0.66
     oprot
    -0.65
    SceneManagement
    -0.64
     jScrollPane
    -0.63
    iastes
    -0.63
    findpost
    -0.62
     AssemblyProduct
    -0.62
    databind
    -0.61
    POSITIVE LOGITS
     inconnu
    0.39
    #+#
    0.39
     inconn
    0.35
    cc
    0.34
    mentes
    0.34
     attesa
    0.33
     sheets
    0.32
     ingenting
    0.32
    MOH
    0.32
    NOT
    0.31
    Activations Density 0.000%

    No Known Activations