© 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. 434
    Prev
    Next
    INDEX
    Explanations

    Preparing and plans

    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
    DeleteBehavior
    -0.60
    JNIEnv
    -0.56
    OGND
    -0.54
    gink
    -0.53
    historical
    -0.53
     dessus
    -0.53
     Winaray
    -0.52
     historiques
    -0.52
    orneys
    -0.52
    historic
    -0.51
    POSITIVE LOGITS
     by
    0.71
    TagHelper
    0.63
    
    0.60
     By
    0.59
     EconPapers
    0.59
     a
    0.57
    enumi
    0.56
     your
    0.52
     springfox
    0.52
     to
    0.49
    Activations Density 0.010%

    No Known Activations