© 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. 0-CLT-HP
    7. 42528
    Prev
    Next
    INDEX
    Explanations

    Marvel

    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
    AddTagHelper
    -0.88
     defaultstate
    -0.84
     MessageBoxIcon
    -0.74
    IntoConstraints
    -0.72
    enumi
    -0.71
    OGND
    -0.71
     jScrollPane
    -0.71
    TypedDataSet
    -0.67
    nodoc
    -0.67
     MainAxisSize
    -0.66
    POSITIVE LOGITS
    ist
    0.57
    ists
    0.57
    irat
    0.57
    itively
    0.53
     douceur
    0.52
    ill
    0.51
    ills
    0.51
    iolo
    0.51
    illi
    0.50
    höhe
    0.50
    Activations Density 0.156%

    No Known Activations