© 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. 20-CLT-HP
    7. 76937
    Prev
    Next
    INDEX
    Explanations

    func

    np_max-act-logits · 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
    PerformLayout
    -0.66
    الدراسه
    -0.57
    StoryboardSegue
    -0.56
    DebuggerNonUser
    -0.54
    zerland
    -0.54
    AccessorTable
    -0.53
    ugd
    -0.53
    principalColumn
    -0.50
     BorderRadius
    -0.50
    addPreferredGap
    -0.50
    POSITIVE LOGITS
     red
    0.68
     yellow
    0.63
    Vidite
    0.62
    Yellow
    0.54
    yellow
    0.54
    umeur
    0.52
     Yellow
    0.51
    ಯ
    0.50
     AppModule
    0.50
    bulos
    0.49
    Activations Density 0.000%

    No Known Activations