© 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. 76613
    Prev
    Next
    INDEX
    Explanations

    Documentation descriptions

    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
     ujednoznacz
    -0.93
    SBATCH
    -0.91
     يتيمه
    -0.88
     препратки
    -0.87
     שוליים
    -0.87
    +:+
    -0.87
     lenker
    -0.87
     esternos
    -0.85
    ніципалі
    -0.82
     intptr
    -0.80
    POSITIVE LOGITS
     all
    0.42
     forms
    0.40
     formes
    0.38
    All
    0.37
    all
    0.35
     All
    0.35
     scale
    0.35
     me
    0.35
     lak
    0.34
    forms
    0.34
    Activations Density 0.000%

    No Known Activations