© 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. 292
    Prev
    Next
    INDEX
    Explanations

    liant

    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
     actionPerformed
    -0.61
    oubliez
    -0.59
     AssemblyTitle
    -0.57
    IBarButtonItem
    -0.55
    Gdx
    -0.55
    XtraReports
    -0.54
    örgy
    -0.53
    SuppressMessage
    -0.52
    tabria
    -0.52
    nambuco
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.72
    __.__
    0.60
     externi
    0.59
     Exactos
    0.57
     estekak
    0.57
    oneofs
    0.51
    öglich
    0.50
    eleste
    0.50
    versation
    0.49
    клопе
    0.49
    Activations Density 0.008%

    No Known Activations