© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40378
    Prev
    Next
    INDEX
    Explanations

    circuit

    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
     circuit
    -1.73
     circuits
    -1.55
    circuit
    -1.52
     Circuit
    -1.46
    Circuit
    -1.41
     Circuits
    -1.41
     CIRCUIT
    -1.35
     circuitos
    -1.30
     circuito
    -1.24
    circuits
    -1.16
    POSITIVE LOGITS
    -
    0.54
    oltre
    0.50
    ous
    0.50
    ,
    0.48
    les
    0.47
     gu
    0.46
    اریخ
    0.44
    GroupLayout
    0.44
    alties
    0.44
    principalTable
    0.43
    Activations Density 0.787%

    No Known Activations