© 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. 38409
    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
    -1.37
    circuit
    -1.34
     Circuit
    -1.20
    Circuit
    -1.19
     CIRCUIT
    -1.09
     circuits
    -1.07
     Circuits
    -1.02
    circuits
    -0.96
     circuito
    -0.88
     circuitry
    -0.84
    POSITIVE LOGITS
    ReusableCell
    0.58
    standing
    0.54
     NSCoder
    0.53
    存于互联网档案馆
    0.51
    ing
    0.49
    rotter
    0.49
    near
    0.48
    bearers
    0.47
    mingen
    0.47
    InjectAttribute
    0.47
    Activations Density 0.250%

    No Known Activations