© 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. 95387
    Prev
    Next
    INDEX
    Explanations

    thought

    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
     thought
    -1.32
     Thought
    -0.76
    thought
    -0.71
    Thought
    -0.71
     THOUGHT
    -0.71
     pensamiento
    -0.46
    ly
    -0.45
     pensée
    -0.45
     believed
    -0.45
     considered
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.92
    rawDesc
    0.87
    PreferredItem
    0.83
    CompleteListener
    0.82
    ########.
    0.82
    SharedDtor
    0.82
     resourceCulture
    0.82
    GraphicsUnit
    0.81
     MonoBehaviour
    0.81
    Rüyada
    0.77
    Activations Density 0.199%

    No Known Activations